feat(run): Ports.FinalGuard — host seam that nudges an announce-then-stop run to deliver its artifact

A run can render an artifact into host storage, end on a text-only stop
turn claiming "Done — sent you the file", and never call the host's
delivery tool — the artifact strands while the user is told it shipped
(mort general run e9e7bf40 2026-07-14, gifsmith run 29170c93 2026-07-12).
The loop has no seam for the host to intervene at the stop turn.

Add Ports.FinalGuard: consulted once when a single-loop run is about to
finalize successfully. A non-empty nudge is appended to the SAME
conversation as the next user turn and the agent runs ONE bounded extra
round (same toolbox/observers, capped at finalNudgeMaxSteps=6) — enough
to deliver the stranded file or correct the final text, not enough to
start a new work spree. Guard panics and nudge-round failures are
isolated: the original successful result always survives. The nudge is
recorded as a final_nudge audit event and appended to the durable
checkpoint transcript.

stageInputFiles now also returns the staged file ids, surfaced to the
guard via FinalState.StagedFileIDs — staged inputs live under run scope
but are the user's attachments, not run-produced artifacts, so an
undelivered-artifact check must exclude them. FinalState.ToolNames lets
a host skip runs that have no delivery tool at all.

Co-Authored-By: Claude Fable 5 <[email protected]>

agentbuiltins/agents/gifsmith/agent.yml

@@ -0,0 +1,49 @@
+# gifsmith — a portable, focused render agent that makes animated GIFs/MP4s via
+# the `gif` skill pack. Shipped by executus (agentbuiltins), run by any host that
+# provides tools with these names, a `thinking` model tier, and the `gif` pack.
+# Nothing here is host-specific — the names are the contract the host binds.
+name: gifsmith
+description: >-
+  Makes a funny animated GIF (or an MP4 when the piece is long or a GIF is too
+  big) from a description, via the gif skill pack. A single-purpose render agent
+  — use it for any request to draw/animate/gif something, including multi-minute
+  bits about people or things that happened.
+model_tier: thinking
+system_prompt: |
+  You make funny animated GIFs and MP4s from a description — often caricatures of
+  the people in the channel or a bit about something that happened. Work by
+  calling tools; do NOT introduce yourself or list capabilities.
+
+  Load the `gif` skill FIRST: call skill_use with name `gif` to get the full
+  recipe (scene/cast planning, the code_exec workspace rules, the bundled encode
+  helper, and the GIF-vs-MP4 size/length decision), then follow it exactly to
+  render and deliver the result. The skill also bundles an encode helper that
+  picks GIF vs MP4 and guarantees a Discord-playable MP4 — use it, don't hand-roll
+  the encode.
+
+  Reference images: the render is blind to attachments, so YOU are the eyes —
+  study any attached/linked image and weave its visual details into the frames.
+  If you can't make it out, proceed from the words.
+low_level_tools:
+  - code_exec
+  - image_describe
+  - send_attachments
+  - file_get_metadata
+  - file_save
+  - think
+skill_packs:
+  - gif
+execution_lane: animate
+max_iterations: 50
+max_tool_calls: 80
+max_runtime_seconds: 1800
+critic_enabled: true
+default_emoji: "🎬"
+state_react:
+  __start__: "🎬"
+  code_exec: "🐍"
+  image_describe: "🖼️"
+  think: "🧠"
+  send_attachments: "📎"
+  __end__: "✅"
+  __error__: "❌"

agentbuiltins/builtins.go

@@ -0,0 +1,24 @@
+// Package agentbuiltins ships executus's canonical builtin agent definitions as
+// an embedded filesystem. They are portable persona manifests
+// (agents/<name>/agent.yml): each references tool NAMES, a model-tier NAME, and
+// skill-pack names — the host binds those to implementations. Nothing here
+// imports a host or a battery, so any executus consumer can seed these via
+// persona.LoadBuiltinAgents (or its own loader that reads the same schema):
+//
+//	persona.LoadBuiltinAgents(ctx, store, agentbuiltins.FS(), skillChecker)
+//
+// Ships:
+//   - gifsmith — a focused GIF/MP4 render agent that uses the `gif` skill pack.
+package agentbuiltins
+
+import (
+	"embed"
+	"io/fs"
+)
+
+//go:embed agents
+var embedded embed.FS
+
+// FS returns the builtin agents tree, rooted so that a loader finds each
+// definition at agents/<name>/agent.yml (the layout LoadBuiltinAgents expects).
+func FS() fs.FS { return embedded }

agentbuiltins/builtins_test.go

@@ -0,0 +1,42 @@
+package agentbuiltins_test
+
+import (
+	"context"
+	"slices"
+	"testing"
+
+	"gitea.stevedudenhoeffer.com/steve/executus/agentbuiltins"
+	"gitea.stevedudenhoeffer.com/steve/executus/persona"
+)
+
+// TestGifsmithLoads proves executus's shipped gifsmith manifest flows through
+// the persona loader and lowers into a RunnableAgent carrying the gif pack — the
+// path a host uses to dogfood it.
+func TestGifsmithLoads(t *testing.T) {
+	ctx := context.Background()
+	store := persona.NewMemory()
+	n, err := persona.LoadBuiltinAgents(ctx, store, agentbuiltins.FS(), nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if n < 1 {
+		t.Fatalf("expected gifsmith seeded, got %d", n)
+	}
+	a, err := store.GetAgentByName(ctx, persona.BuiltinAgentOwnerID, "gifsmith")
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(a.SkillPacks) != 1 || a.SkillPacks[0] != "gif" {
+		t.Errorf("skill_packs = %v", a.SkillPacks)
+	}
+	if a.ModelTier != "thinking" {
+		t.Errorf("model_tier = %q (want a portable tier name)", a.ModelTier)
+	}
+	if !slices.Contains(a.LowLevelTools, "code_exec") || !slices.Contains(a.LowLevelTools, "send_attachments") {
+		t.Errorf("low_level_tools missing render/deliver tools: %v", a.LowLevelTools)
+	}
+	// The pack must survive the lowering the executor consumes.
+	if ra := a.ToRunnable(); len(ra.SkillPacks) != 1 || ra.SkillPacks[0] != "gif" {
+		t.Errorf("RunnableAgent.SkillPacks = %v", ra.SkillPacks)
+	}
+}

persona/agent.go

@@ -86,6 +86,9 @@ type Agent struct {
 	SkillPalette    []string // skill IDs/names
 	SubAgentPalette []string // agent IDs/names
 	LowLevelTools   []string // skilltools registry names
+	// SkillPacks names SKILL.md skill-pack subscriptions activated for a run via
+	// run.Ports.SkillPacks (catalog folded into the prompt + a skill_use loader).
+	SkillPacks []string
 
 	// Personalization (Phase 5 reads these). Each layer name maps to
 	// a registered PersonalizationProvider that returns text appended

persona/builtin_loader.go

@@ -291,6 +291,9 @@ func resolveExtends(child, parent *Agent) {
 	if child.LowLevelTools == nil {
 		child.LowLevelTools = parent.LowLevelTools
 	}
+	if child.SkillPacks == nil {
+		child.SkillPacks = parent.SkillPacks
+	}
 	if child.PersonalizationSources == nil {
 		child.PersonalizationSources = parent.PersonalizationSources
 	}
@@ -456,6 +459,7 @@ type builtinAgentManifest struct {
 	SkillPalette    []string `yaml:"skill_palette"`
 	SubAgentPalette []string `yaml:"sub_agent_palette"`
 	LowLevelTools   []string `yaml:"low_level_tools"`
+	SkillPacks      []string `yaml:"skill_packs"`
 
 	PersonalizationSources []string `yaml:"personalization_sources"`
 
@@ -562,6 +566,7 @@ func decodeAgentManifest(data []byte) (*Agent, error) {
 		SkillPalette:             m.SkillPalette,
 		SubAgentPalette:          m.SubAgentPalette,
 		LowLevelTools:            m.LowLevelTools,
+		SkillPacks:               m.SkillPacks,
 		PersonalizationSources:   m.PersonalizationSources,
 		Schedule:                 strings.TrimSpace(m.Schedule),
 		WebhookIPAllowlist:       allowlist,

persona/runnable.go

@@ -18,6 +18,7 @@ func (a *Agent) ToRunnable() run.RunnableAgent {
 		LowLevelTools:   a.LowLevelTools,
 		SkillPalette:    a.SkillPalette,
 		SubAgentPalette: a.SubAgentPalette,
+		SkillPacks:      a.SkillPacks,
 		Critic: run.CriticConfig{
 			Enabled:            a.CriticEnabled,
 			BackstopMultiplier: a.CriticBackstopMultiplier,

run/agent.go

@@ -44,6 +44,11 @@ type RunnableAgent struct {
 	LowLevelTools   []string
 	SkillPalette    []string
 	SubAgentPalette []string
+	// SkillPacks names SKILL.md skill-pack subscriptions activated for the run
+	// via Ports.SkillPacks: each pack's name+description joins a catalog folded
+	// into the system prompt, and a skill_use tool loads a pack's body on demand
+	// (progressive disclosure). nil Ports.SkillPacks => inert.
+	SkillPacks []string
 
 	// Phases optionally model a multi-step pipeline (each phase its own prompt
 	// + tier + tools). An empty slice is a single-phase run — the common case.

run/executor.go

@@ -275,6 +275,32 @@ func (e *Executor) Run(ctx context.Context, ra RunnableAgent, inv tool.Invocatio
 		postRun = st.PostRun
 	}
 
+	// Skill packs: resolve the agent's subscribed packs into a catalog (folded
+	// into the system prompt) + a skill_use loader tool added to the toolbox.
+	// nil-safe; activation failures are non-fatal — the run proceeds without
+	// packs rather than dying on a fetch/cache miss.
+	if len(ra.SkillPacks) > 0 && e.cfg.Ports.SkillPacks != nil {
+		instr, packTools, aerr := e.cfg.Ports.SkillPacks.ActivateSkillPacks(ctx, ra.SkillPacks, inv.RunID, ra.ID)
+		if aerr != nil {
+			slog.Warn("run: skill-pack activation failed; continuing without packs", "run_id", inv.RunID, "error", aerr)
+		} else {
+			for _, t := range packTools {
+				if err := toolbox.Add(t); err != nil {
+					res.Err = fmt.Errorf("add skill-pack tool: %w", err)
+					e.finishAudit(ctx, rec, "error", res, started, res.Err)
+					return res
+				}
+			}
+			if instr != "" {
+				if ra.SystemPrompt != "" {
+					ra.SystemPrompt += "\n\n" + instr
+				} else {
+					ra.SystemPrompt = instr
+				}
+			}
+		}
+	}
+
 	// Run context: detached from the caller's deadline so a lane/queue wait doesn't
 	// eat the run budget (mort's V10 lesson). Caller cancellation still propagates
 	// via MergeCancellation. Created BEFORE the step observer so the observer
@@ -403,8 +429,10 @@ func (e *Executor) Run(ctx context.Context, ra RunnableAgent, inv tool.Invocatio
 	// store and fold an [ATTACHED FILES] descriptor into the prompt so the agent
 	// can reach them by file_id. No-op when Ports.InputFiles is nil or there are
 	// no files. Done after the model/toolbox build but before the loop, so the
-	// descriptor rides the very first user turn.
-	input = e.stageInputFiles(runCtx, inv.RunID, ra.ID, inv.InputFiles, input)
+	// descriptor rides the very first user turn. The staged file ids are kept for
+	// the FinalGuard: they live under run scope but are the user's INPUTS, not
+	// run-produced artifacts, so an undelivered-artifact check must exclude them.
+	input, stagedFileIDs := e.stageInputFiles(runCtx, inv.RunID, ra.ID, inv.InputFiles, input)
 	// One WithSteer drains BOTH the session mailbox (a tool's AttachImages) and
 	// the critic's nudges before each step.
 	steer := func() []llm.Message { return append(mailbox.drain(), critic.drainSteer()...) }
@@ -426,6 +454,10 @@ func (e *Executor) Run(ctx context.Context, ra RunnableAgent, inv tool.Invocatio
 		// step responses, not the loop's compacted history) — a host that caps size
 		// bounds it. A recovered run seeds the saved transcript and continues.
 		obs := stepObserver
+		// noteCheckpoint appends an out-of-loop message (the FinalGuard nudge) to
+		// the checkpoint transcript so a shutdown-resume of a nudged run replays
+		// the nudge turn too. nil when the run is non-durable.
+		var noteCheckpoint func(llm.Message)
 		if ckpt != nil {
 			var acc []llm.Message
 			if resuming {
@@ -443,6 +475,7 @@ func (e *Executor) Run(ctx context.Context, ra RunnableAgent, inv tool.Invocatio
 				}
 				_ = ckpt.Save(runCtx, RunCheckpointState{Messages: acc, Iteration: s.Index + 1})
 			}
+			noteCheckpoint = func(m llm.Message) { acc = append(acc, m) }
 		}
 		opts := append([]agent.Option{
 			agent.WithToolbox(toolbox),
@@ -457,6 +490,50 @@ func (e *Executor) Run(ctx context.Context, ra RunnableAgent, inv tool.Invocatio
 		} else {
 			runRes, runErr = runAgent(runCtx, ag, input, inv.Images, agent.WithSteer(steer))
 		}
+
+		// FinalGuard (optional): the run finished successfully — before the result
+		// is finalized, let the host inspect it for undelivered work (the
+		// announce-then-stop failure: an artifact rendered into run storage, a
+		// final text claiming "Done", and no delivery tool call). A non-empty
+		// nudge runs ONE bounded extra round on the same conversation: same model,
+		// same toolbox, same observers (audit/steps/critic all see it), but a
+		// small fixed step cap so a misread nudge can't start a new work spree.
+		// The nudge round's failure is non-fatal — the original successful result
+		// stands (any attachments it queued before failing still deliver).
+		if runErr == nil && runRes != nil && e.cfg.Ports.FinalGuard != nil {
+			state := FinalState{
+				Output:        runRes.Output,
+				ToolNames:     toolboxNames(toolbox),
+				StagedFileIDs: stagedFileIDs,
+			}
+			if nudge := safeFinalNudge(runCtx, e.cfg.Ports.FinalGuard, info, state); nudge != "" {
+				if rec != nil {
+					rec.LogEvent("final_nudge", map[string]any{"nudge": nudge})
+				}
+				if noteCheckpoint != nil {
+					noteCheckpoint(llm.UserText(nudge))
+				}
+				nudgeOpts := append([]agent.Option{
+					agent.WithToolbox(toolbox),
+					agent.WithMaxSteps(finalNudgeMaxSteps),
+					agent.WithStepObserver(obs),
+				}, sharedOpts...)
+				nudgeAg := agent.New(model, e.systemPrompt(ra), nudgeOpts...)
+				nudgeRes, nudgeErr := nudgeAg.Run(runCtx, nudge,
+					agent.WithSteer(steer), agent.WithHistory(runRes.Messages))
+				if nudgeRes != nil {
+					// The extra round's tokens are real spend either way.
+					runRes.Usage.Add(nudgeRes.Usage)
+				}
+				if nudgeErr != nil {
+					slog.Warn("run: final-nudge round failed; keeping original result",
+						"run_id", inv.RunID, "error", nudgeErr)
+				} else if nudgeRes != nil {
+					runRes.Output = nudgeRes.Output
+					runRes.Messages = nudgeRes.Messages
+				}
+			}
+		}
 	} else {
 		// Multi-phase pipeline: each phase runs its own prompt/tier/tools/step-cap
 		// sequentially, threading outputs through {{.<PhaseName>}} templates. The

run/final_guard.go

@@ -0,0 +1,80 @@
+package run
+
+import (
+	"context"
+	"log/slog"
+
+	"gitea.stevedudenhoeffer.com/steve/majordomo/llm"
+)
+
+// FinalGuard is the optional host seam consulted when a single-loop run is
+// about to finalize SUCCESSFULLY (the model produced a final answer and no run
+// error occurred). It exists for the "announce-then-stop" failure: an agent
+// renders an artifact into host storage, narrates "Done — sent you the file",
+// and ends the run without ever calling the host's delivery tool — so nothing
+// reaches the user while the final text claims otherwise (observed live:
+// gifsmith run 29170c93 2026-07-12, general run e9e7bf40 2026-07-14).
+//
+// FinalNudge returns "" to let the run finish as-is (the overwhelmingly common
+// case — the host should make its check cheap), or a non-empty nudge message.
+// A non-empty nudge sends the loop back for ONE bounded extra round: the nudge
+// is appended to the SAME conversation as the next user turn and the agent
+// runs again with the same toolbox, capped at finalNudgeMaxSteps steps — enough
+// to deliver a stranded artifact (or correct the final text), not enough to
+// start a new project. The guard is consulted at most ONCE per run; the nudge
+// round's own stop turn is final. Multi-phase runs are not guarded (their
+// output contract is the phase pipeline's, not a delivery surface's).
+//
+// The call runs on the run goroutine, inside the run's deadline, and is
+// panic-isolated: a guard panic is logged and treated as "" (the run's
+// successful result must never be lost to a guard bug).
+type FinalGuard interface {
+	FinalNudge(ctx context.Context, info RunInfo, state FinalState) string
+}
+
+// FinalState is the snapshot a FinalGuard receives about the finishing run.
+type FinalState struct {
+	// Output is the run's final answer text (what the host would deliver).
+	Output string
+	// ToolNames lists the tools that were available to the run, so a guard can
+	// skip nudging a run that has no way to act (e.g. no send_attachments).
+	ToolNames []string
+	// StagedFileIDs are the file ids the executor staged from the invocation's
+	// input attachments (Ports.InputFiles). They live under the run's file scope
+	// but are the USER's inputs, not run-produced artifacts — a guard checking
+	// for undelivered artifacts must exclude them.
+	StagedFileIDs []string
+}
+
+// finalNudgeMaxSteps caps the nudge round's tool-dispatch steps. Delivering a
+// stranded artifact needs at most a file_list + a send_attachments + a final
+// text turn; the cap keeps a model that misreads the nudge from launching a
+// whole new work spree on the host's budget.
+const finalNudgeMaxSteps = 6
+
+// safeFinalNudge consults the guard behind a recover so a guard panic degrades
+// to "no nudge" instead of converting a successful run into a panic-error (the
+// executor's top-level recover would otherwise stamp res.Err).
+func safeFinalNudge(ctx context.Context, g FinalGuard, info RunInfo, state FinalState) (nudge string) {
+	defer func() {
+		if r := recover(); r != nil {
+			slog.Error("run: FinalGuard panicked; skipping nudge",
+				"run_id", info.RunID, "panic", r)
+			nudge = ""
+		}
+	}()
+	return g.FinalNudge(ctx, info, state)
+}
+
+// toolboxNames flattens the run toolbox's tool names for FinalState (nil-safe).
+func toolboxNames(b *llm.Toolbox) []string {
+	if b == nil {
+		return nil
+	}
+	tools := b.Tools()
+	names := make([]string, 0, len(tools))
+	for _, t := range tools {
+		names = append(names, t.Name)
+	}
+	return names
+}

run/final_guard_test.go

@@ -0,0 +1,287 @@
+package run
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"testing"
+
+	"gitea.stevedudenhoeffer.com/steve/majordomo/llm"
+	"gitea.stevedudenhoeffer.com/steve/majordomo/provider/fake"
+
+	"gitea.stevedudenhoeffer.com/steve/executus/tool"
+)
+
+// guardFunc adapts a func to FinalGuard, counting calls and capturing the
+// snapshot it received.
+type guardFunc struct {
+	nudge func(info RunInfo, state FinalState) string
+	calls int
+	info  RunInfo
+	state FinalState
+}
+
+func (g *guardFunc) FinalNudge(_ context.Context, info RunInfo, state FinalState) string {
+	g.calls++
+	g.info = info
+	g.state = state
+	return g.nudge(info, state)
+}
+
+// eventRecorder is captureRecorder plus LogEvent capture (for the final_nudge
+// audit event).
+type eventRecorder struct {
+	captureRecorder
+	events []string
+}
+
+func (r *eventRecorder) LogEvent(eventType string, _ map[string]any) {
+	r.events = append(r.events, eventType)
+}
+
+// TestFinalGuardNudgeRunsOneExtraRound is the core announce-then-stop fix: the
+// model stops with "Done — sent!" (nothing delivered), the guard returns a
+// nudge, and the SAME conversation runs one more round — here a tool call then
+// a corrected final answer. The guard is consulted exactly once (the nudge
+// round's own stop is final), and the audit log records the nudge.
+func TestFinalGuardNudgeRunsOneExtraRound(t *testing.T) {
+	fp := fake.New("fake")
+	fp.Enqueue("m",
+		fake.Reply("Done — sent you the file!"),
+		// Nudge round: an (unregistered → tolerated error result) delivery call,
+		// then the corrected final answer.
+		fake.ReplyWith(llm.Response{ToolCalls: []llm.ToolCall{{ID: "c1", Name: "send_attachments", Arguments: []byte(`{}`)}}}),
+		fake.Reply("delivered for real"),
+	)
+	m, _ := fp.Model("m")
+	rec := &eventRecorder{}
+	guard := &guardFunc{nudge: func(RunInfo, FinalState) string { return "you did not deliver the file" }}
+	ex := New(Config{
+		Registry: tool.NewRegistry(),
+		Models:   func(ctx context.Context, _ string) (context.Context, llm.Model, error) { return ctx, m, nil },
+		Ports: Ports{
+			Audit:      auditFunc{start: func(RunInfo) RunRecorder { return rec }},
+			FinalGuard: guard,
+		},
+	})
+
+	res := ex.Run(context.Background(),
+		RunnableAgent{Name: "g", ModelTier: "m"},
+		tool.Invocation{RunID: "r-nudge", CallerID: "c"}, "make me a file")
+
+	if res.Err != nil {
+		t.Fatalf("run error: %v", res.Err)
+	}
+	if res.Output != "delivered for real" {
+		t.Fatalf("output = %q, want the nudge round's answer", res.Output)
+	}
+	if guard.calls != 1 {
+		t.Fatalf("guard consulted %d times, want exactly 1 (no re-guard of the nudge round)", guard.calls)
+	}
+	if guard.info.RunID != "r-nudge" {
+		t.Errorf("guard info.RunID = %q", guard.info.RunID)
+	}
+	if guard.state.Output != "Done — sent you the file!" {
+		t.Errorf("guard state.Output = %q, want the pre-nudge final text", guard.state.Output)
+	}
+	var sawNudgeEvent bool
+	for _, ev := range rec.events {
+		if ev == "final_nudge" {
+			sawNudgeEvent = true
+		}
+	}
+	if !sawNudgeEvent {
+		t.Errorf("audit events %v missing final_nudge", rec.events)
+	}
+	if rec.stats.Output != "delivered for real" {
+		t.Errorf("audit close output = %q, want the nudged output", rec.stats.Output)
+	}
+}
+
+// TestFinalGuardEmptyNudgeNoExtraRound: a guard returning "" adds zero model
+// calls — the common path stays one round.
+func TestFinalGuardEmptyNudgeNoExtraRound(t *testing.T) {
+	fp := fake.New("fake")
+	fp.Enqueue("m", fake.Reply("plain answer"))
+	m, _ := fp.Model("m")
+	guard := &guardFunc{nudge: func(RunInfo, FinalState) string { return "" }}
+	ex := New(Config{
+		Registry: tool.NewRegistry(),
+		Models:   func(ctx context.Context, _ string) (context.Context, llm.Model, error) { return ctx, m, nil },
+		Ports:    Ports{FinalGuard: guard},
+	})
+
+	res := ex.Run(context.Background(),
+		RunnableAgent{ModelTier: "m"}, tool.Invocation{RunID: "r"}, "hi")
+
+	if res.Err != nil {
+		t.Fatalf("run error: %v", res.Err)
+	}
+	if res.Output != "plain answer" {
+		t.Fatalf("output = %q", res.Output)
+	}
+	if guard.calls != 1 {
+		t.Errorf("guard consulted %d times, want 1", guard.calls)
+	}
+	if n := fp.CallCount("m"); n != 1 {
+		t.Errorf("model called %d times, want 1 (empty nudge must not re-run)", n)
+	}
+}
+
+// TestFinalGuardNudgeRoundFailureKeepsResult: the nudge round erroring (model
+// failure, deadline, step cap) must NOT damage the original successful result.
+func TestFinalGuardNudgeRoundFailureKeepsResult(t *testing.T) {
+	fp := fake.New("fake")
+	fp.Enqueue("m",
+		fake.Reply("original answer"),
+		fake.Fail(errors.New("provider fell over")),
+	)
+	m, _ := fp.Model("m")
+	guard := &guardFunc{nudge: func(RunInfo, FinalState) string { return "deliver it" }}
+	ex := New(Config{
+		Registry: tool.NewRegistry(),
+		Models:   func(ctx context.Context, _ string) (context.Context, llm.Model, error) { return ctx, m, nil },
+		Ports:    Ports{FinalGuard: guard},
+	})
+
+	res := ex.Run(context.Background(),
+		RunnableAgent{ModelTier: "m"}, tool.Invocation{RunID: "r"}, "hi")
+
+	if res.Err != nil {
+		t.Fatalf("a failed nudge round must not fail the run: %v", res.Err)
+	}
+	if res.Output != "original answer" {
+		t.Fatalf("output = %q, want the original preserved", res.Output)
+	}
+}
+
+// TestFinalGuardNotConsultedOnRunError: a failed run is never nudged — the
+// guard exists for successful-but-undelivered finishes only.
+func TestFinalGuardNotConsultedOnRunError(t *testing.T) {
+	fp := fake.New("fake")
+	fp.Enqueue("m", fake.Fail(errors.New("boom")))
+	m, _ := fp.Model("m")
+	guard := &guardFunc{nudge: func(RunInfo, FinalState) string { return "nudge" }}
+	ex := New(Config{
+		Registry: tool.NewRegistry(),
+		Models:   func(ctx context.Context, _ string) (context.Context, llm.Model, error) { return ctx, m, nil },
+		Ports:    Ports{FinalGuard: guard},
+	})
+
+	res := ex.Run(context.Background(),
+		RunnableAgent{ModelTier: "m"}, tool.Invocation{RunID: "r"}, "hi")
+
+	if res.Err == nil {
+		t.Fatal("expected a run error")
+	}
+	if guard.calls != 0 {
+		t.Errorf("guard consulted %d times on a failed run, want 0", guard.calls)
+	}
+}
+
+// TestFinalGuardPanicIsolated: a panicking guard degrades to "no nudge" — the
+// successful result survives untouched.
+func TestFinalGuardPanicIsolated(t *testing.T) {
+	fp := fake.New("fake")
+	fp.Enqueue("m", fake.Reply("safe answer"))
+	m, _ := fp.Model("m")
+	ex := New(Config{
+		Registry: tool.NewRegistry(),
+		Models:   func(ctx context.Context, _ string) (context.Context, llm.Model, error) { return ctx, m, nil },
+		Ports:    Ports{FinalGuard: panicGuard{}},
+	})
+
+	res := ex.Run(context.Background(),
+		RunnableAgent{ModelTier: "m"}, tool.Invocation{RunID: "r"}, "hi")
+
+	if res.Err != nil {
+		t.Fatalf("guard panic must not fail the run: %v", res.Err)
+	}
+	if res.Output != "safe answer" {
+		t.Fatalf("output = %q", res.Output)
+	}
+}
+
+type panicGuard struct{}
+
+func (panicGuard) FinalNudge(context.Context, RunInfo, FinalState) string {
+	panic("guard bug")
+}
+
+// TestFinalGuardReceivesToolNamesAndStagedIDs: the guard's snapshot carries the
+// run's tool names (via ExtraTools here) and the input-staged file ids, so a
+// host can skip runs that can't deliver and exclude the user's own attachments.
+func TestFinalGuardReceivesToolNamesAndStagedIDs(t *testing.T) {
+	fp := fake.New("fake")
+	fp.Enqueue("m", fake.Reply("done"))
+	m, _ := fp.Model("m")
+	guard := &guardFunc{nudge: func(RunInfo, FinalState) string { return "" }}
+	ex := New(Config{
+		Registry: tool.NewRegistry(),
+		Models:   func(ctx context.Context, _ string) (context.Context, llm.Model, error) { return ctx, m, nil },
+		Ports: Ports{
+			FinalGuard: guard,
+			InputFiles: guardStager(func(name string) string { return "staged-" + name }),
+		},
+	})
+
+	res := ex.Run(context.Background(),
+		RunnableAgent{ModelTier: "m"},
+		tool.Invocation{
+			RunID: "r",
+			ExtraTools: []llm.Tool{{
+				Name:        "send_attachments",
+				Description: "deliver",
+				Handler:     func(context.Context, json.RawMessage) (any, error) { return "ok", nil },
+			}},
+			InputFiles: []tool.InputFile{{Name: "input.wav", MimeType: "audio/wave", Data: []byte("x")}},
+		}, "hi")
+
+	if res.Err != nil {
+		t.Fatalf("run error: %v", res.Err)
+	}
+	var sawTool bool
+	for _, n := range guard.state.ToolNames {
+		if n == "send_attachments" {
+			sawTool = true
+		}
+	}
+	if !sawTool {
+		t.Errorf("guard state.ToolNames = %v, want send_attachments present", guard.state.ToolNames)
+	}
+	if len(guard.state.StagedFileIDs) != 1 || guard.state.StagedFileIDs[0] != "staged-input.wav" {
+		t.Errorf("guard state.StagedFileIDs = %v, want [staged-input.wav]", guard.state.StagedFileIDs)
+	}
+}
+
+// guardStager maps an input file's name to a deterministic file id.
+type guardStager func(name string) string
+
+func (f guardStager) StageInputFile(_ context.Context, _, _, name, _ string, _ []byte) (string, error) {
+	return f(name), nil
+}
+
+// TestFinalGuardSkipsMultiPhaseRuns: a phase pipeline's output contract is the
+// pipeline's, not a delivery surface's — the guard must not be consulted.
+func TestFinalGuardSkipsMultiPhaseRuns(t *testing.T) {
+	fp := fake.New("fake")
+	fp.Enqueue("m", fake.Reply("phase-out"))
+	m, _ := fp.Model("m")
+	guard := &guardFunc{nudge: func(RunInfo, FinalState) string { return "nudge" }}
+	ex := New(Config{
+		Registry: tool.NewRegistry(),
+		Models:   func(ctx context.Context, _ string) (context.Context, llm.Model, error) { return ctx, m, nil },
+		Ports:    Ports{FinalGuard: guard},
+	})
+
+	res := ex.Run(context.Background(),
+		RunnableAgent{ModelTier: "m", Phases: []Phase{{Name: "a", SystemPrompt: "do a"}}},
+		tool.Invocation{RunID: "r"}, "hi")
+
+	if res.Err != nil {
+		t.Fatalf("run error: %v", res.Err)
+	}
+	if guard.calls != 0 {
+		t.Errorf("guard consulted %d times on a phase run, want 0", guard.calls)
+	}
+}

run/input_files.go

@@ -30,10 +30,11 @@ const maxInputFiles = 32
 //
 // Best-effort: a nil stager, no files, or a per-file save error degrades to
 // "skip that file" — the run still proceeds. Returns the (possibly augmented)
-// prompt.
-func (e *Executor) stageInputFiles(ctx context.Context, runID, agentID string, files []tool.InputFile, prompt string) string {
+// prompt plus the staged file ids (for the FinalGuard: staged inputs live under
+// run scope but are not run-produced artifacts).
+func (e *Executor) stageInputFiles(ctx context.Context, runID, agentID string, files []tool.InputFile, prompt string) (string, []string) {
 	if e.cfg.Ports.InputFiles == nil || len(files) == 0 {
-		return prompt
+		return prompt, nil
 	}
 	// Count cap: bound how many attachments one run can stage, independent of the
 	// per-file byte cap (defense-in-depth against a flood of tiny files).
@@ -87,7 +88,11 @@ func (e *Executor) stageInputFiles(ctx context.Context, runID, agentID string, f
 		staged = append(staged, stagedFile{name: name, mime: mime, fileID: sanitizeField(fileID), size: len(f.Data)})
 	}
 	if len(staged) == 0 {
-		return prompt
+		return prompt, nil
+	}
+	stagedIDs := make([]string, 0, len(staged))
+	for _, s := range staged {
+		stagedIDs = append(stagedIDs, s.fileID)
 	}
 
 	var b strings.Builder
@@ -101,9 +106,9 @@ func (e *Executor) stageInputFiles(ctx context.Context, runID, agentID string, f
 	}
 
 	if strings.TrimSpace(prompt) == "" {
-		return b.String()
+		return b.String(), stagedIDs
 	}
-	return prompt + "\n\n" + b.String()
+	return prompt + "\n\n" + b.String(), stagedIDs
 }
 
 // sanitizeName reduces an untrusted attachment filename to a safe base name. It

run/input_files_test.go

@@ -44,7 +44,7 @@ func newStagerExecutor(s InputFileStager) *Executor {
 func TestStageInputFiles(t *testing.T) {
 	st := &stagerFunc{}
 	ex := newStagerExecutor(st)
-	out := ex.stageInputFiles(context.Background(), "run-1", "agent-1",
+	out, _ := ex.stageInputFiles(context.Background(), "run-1", "agent-1",
 		[]tool.InputFile{{Name: "clip.mp3", MimeType: "audio/mpeg", Data: []byte("abcd")}},
 		"transcribe this")
 
@@ -65,7 +65,7 @@ func TestStageInputFiles(t *testing.T) {
 // drops the run.
 func TestStageInputFilesNoStager(t *testing.T) {
 	ex := newStagerExecutor(nil) // Ports.InputFiles == nil
-	out := ex.stageInputFiles(context.Background(), "r", "a",
+	out, _ := ex.stageInputFiles(context.Background(), "r", "a",
 		[]tool.InputFile{{Name: "x.bin", Data: []byte("z")}}, "prompt")
 	if out != "prompt" {
 		t.Errorf("nil stager changed the prompt: %q", out)
@@ -75,7 +75,7 @@ func TestStageInputFilesNoStager(t *testing.T) {
 // TestStageInputFilesNoFiles: no attachments leaves the prompt untouched.
 func TestStageInputFilesNoFiles(t *testing.T) {
 	ex := newStagerExecutor(&stagerFunc{})
-	out := ex.stageInputFiles(context.Background(), "r", "a", nil, "prompt")
+	out, _ := ex.stageInputFiles(context.Background(), "r", "a", nil, "prompt")
 	if out != "prompt" {
 		t.Errorf("no files changed the prompt: %q", out)
 	}
@@ -86,7 +86,7 @@ func TestStageInputFilesNoFiles(t *testing.T) {
 func TestStageInputFilesDedup(t *testing.T) {
 	st := &stagerFunc{}
 	ex := newStagerExecutor(st)
-	out := ex.stageInputFiles(context.Background(), "r", "a", []tool.InputFile{
+	out, _ := ex.stageInputFiles(context.Background(), "r", "a", []tool.InputFile{
 		{Name: "a.wav", MimeType: "audio/wav", Data: []byte("1")},
 		{Name: "a.wav", MimeType: "audio/wav", Data: []byte("2")},
 	}, "go")
@@ -106,13 +106,13 @@ func TestStageInputFilesDedup(t *testing.T) {
 func TestStageInputFilesSkipsBad(t *testing.T) {
 	// Empty data → skipped; with no good files the prompt is returned as-is.
 	ex := newStagerExecutor(&stagerFunc{})
-	if out := ex.stageInputFiles(context.Background(), "r", "a",
+	if out, _ := ex.stageInputFiles(context.Background(), "r", "a",
 		[]tool.InputFile{{Name: "empty.bin", Data: nil}}, "p"); out != "p" {
 		t.Errorf("empty file should be skipped, got %q", out)
 	}
 	// A stager error → that file is dropped; nothing staged → prompt unchanged.
 	exErr := newStagerExecutor(&stagerFunc{err: errors.New("disk full")})
-	if out := exErr.stageInputFiles(context.Background(), "r", "a",
+	if out, _ := exErr.stageInputFiles(context.Background(), "r", "a",
 		[]tool.InputFile{{Name: "x.bin", Data: []byte("z")}}, "p"); out != "p" {
 		t.Errorf("save error should drop the file and leave the prompt, got %q", out)
 	}
@@ -124,7 +124,7 @@ func TestStageInputFilesOversize(t *testing.T) {
 	st := &stagerFunc{}
 	ex := newStagerExecutor(st)
 	big := make([]byte, maxInputFileBytes+1)
-	out := ex.stageInputFiles(context.Background(), "r", "a",
+	out, _ := ex.stageInputFiles(context.Background(), "r", "a",
 		[]tool.InputFile{{Name: "huge.bin", Data: big}}, "p")
 	if out != "p" || len(st.staged) != 0 {
 		t.Errorf("oversized file should be skipped: out=%q staged=%d", out, len(st.staged))
@@ -177,7 +177,7 @@ func TestSanitizeName(t *testing.T) {
 func TestStageInputFilesSanitizesTraversal(t *testing.T) {
 	st := &stagerFunc{}
 	ex := newStagerExecutor(st)
-	out := ex.stageInputFiles(context.Background(), "r", "a",
+	out, _ := ex.stageInputFiles(context.Background(), "r", "a",
 		[]tool.InputFile{{Name: "../../../etc/passwd", MimeType: "text/plain", Data: []byte("x")}}, "go")
 	if len(st.staged) != 1 || st.staged[0].name != "passwd" {
 		t.Fatalf("staged name = %+v, want passwd", st.staged)
@@ -202,7 +202,7 @@ func TestSanitizeFieldStripsBidiAndControl(t *testing.T) {
 func TestStageInputFilesSanitizesMime(t *testing.T) {
 	st := &stagerFunc{}
 	ex := newStagerExecutor(st)
-	out := ex.stageInputFiles(context.Background(), "r", "a",
+	out, _ := ex.stageInputFiles(context.Background(), "r", "a",
 		[]tool.InputFile{{Name: "c.wav", MimeType: "audio/wav\ninjected", Data: []byte("x")}}, "go")
 	if len(st.staged) != 1 || strings.ContainsAny(st.staged[0].mime, "\n\r") {
 		t.Errorf("mime not sanitized before staging: %+v", st.staged)
@@ -216,7 +216,7 @@ func TestStageInputFilesSanitizesMime(t *testing.T) {
 // file (no blank file_id in the descriptor).
 func TestStageInputFilesEmptyFileID(t *testing.T) {
 	ex := newStagerExecutor(emptyIDStager{})
-	out := ex.stageInputFiles(context.Background(), "r", "a",
+	out, _ := ex.stageInputFiles(context.Background(), "r", "a",
 		[]tool.InputFile{{Name: "x.bin", Data: []byte("z")}}, "p")
 	if out != "p" {
 		t.Errorf("empty file_id should drop the file, got %q", out)

run/ports.go

@@ -49,6 +49,27 @@ type Ports struct {
 	// are silently ignored (the run still proceeds, text-only). The bytes are
 	// never inlined into the model context — the LLM can't read raw audio/binary.
 	InputFiles InputFileStager
+	// SkillPacks activates a RunnableAgent.SkillPacks (SKILL.md subscriptions)
+	// for the run: it folds a catalog into the system prompt and adds a skill_use
+	// loader tool. nil = SkillPacks are inert. The executus/skillpack battery
+	// ships a default impl (skillpack.Activator).
+	SkillPacks SkillPackActivator
+	// FinalGuard is consulted when a single-loop run is about to finalize
+	// successfully; a non-empty nudge sends the loop back for one bounded extra
+	// round (the announce-then-stop undelivered-artifact check). nil = runs
+	// finalize unguarded. See FinalGuard in final_guard.go.
+	FinalGuard FinalGuard
+}
+
+// SkillPackActivator resolves an agent's subscribed skill-pack names for a run
+// into system-prompt instructions (a catalog of what's available on demand) and
+// the tools that back them (a single skill_use loader). It receives the run +
+// subject ids so the impl can scope any per-run file staging. It returns "" +
+// nil when nothing resolves; activation errors are non-fatal to the run. Defined
+// here (the consumer) so the battery satisfies it structurally without importing
+// run — the same inversion as the other ports.
+type SkillPackActivator interface {
+	ActivateSkillPacks(ctx context.Context, names []string, runID, subjectID string) (instructions string, tools []llm.Tool, err error)
 }
 
 // InputFileStager persists a single non-image input attachment into a host file

skillpack/activator.go

@@ -0,0 +1,58 @@
+package skillpack
+
+import (
+	"context"
+	"errors"
+
+	"gitea.stevedudenhoeffer.com/steve/majordomo/llm"
+)
+
+// Activator adapts the battery to executus/run's SkillPackActivator port: given
+// an agent's subscribed pack names, it resolves them to their pinned packs and
+// returns the catalog instructions + the skill_use tool the run injects. It
+// satisfies run.SkillPackActivator structurally — no import of run — so the
+// battery stays run-agnostic (the same inversion as the other batteries).
+//
+// StagerFor, when set, builds the per-run BundleStager (a host plumbs bundled
+// files into its own run-scoped storage from the run + subject ids); nil means
+// skill_use lists a pack's bundled filenames without staging them.
+type Activator struct {
+	Cache     PackCache
+	Subs      Store
+	StagerFor func(runID, subjectID string) BundleStager
+}
+
+// ActivateSkillPacks implements run.SkillPackActivator. Unknown or disabled pack
+// names are skipped; it returns "" + nil when nothing resolves.
+func (a *Activator) ActivateSkillPacks(ctx context.Context, names []string, runID, subjectID string) (string, []llm.Tool, error) {
+	if a == nil || a.Subs == nil || a.Cache == nil || len(names) == 0 {
+		return "", nil, nil
+	}
+	chosen := make([]Subscription, 0, len(names))
+	for _, n := range names {
+		sub, err := a.Subs.GetByName(ctx, n)
+		if errors.Is(err, ErrNotFound) {
+			continue
+		}
+		if err != nil {
+			return "", nil, err
+		}
+		if !sub.Enabled {
+			continue
+		}
+		chosen = append(chosen, *sub)
+	}
+	packs, err := Resolve(ctx, a.Cache, chosen)
+	if err != nil {
+		return "", nil, err
+	}
+	var stager BundleStager
+	if a.StagerFor != nil {
+		stager = a.StagerFor(runID, subjectID)
+	}
+	sk := Activate(packs, stager)
+	if sk == nil {
+		return "", nil, nil
+	}
+	return sk.Instructions(), sk.Tools().Tools(), nil
+}

skillpack/activator_test.go

@@ -0,0 +1,50 @@
+package skillpack
+
+import (
+	"context"
+	"testing"
+)
+
+func TestActivator(t *testing.T) {
+	ctx := context.Background()
+	src := &fakeSource{tree: packTree("alpha", "do alpha things"), ref: "r1"}
+	y := newTestSyncer(src)
+	if _, err := y.Subscribe(ctx, src, "main", "steve"); err != nil {
+		t.Fatal(err)
+	}
+
+	staged := 0
+	act := &Activator{
+		Cache: y.Cache, Subs: y.Subs,
+		StagerFor: func(runID, subjectID string) BundleStager {
+			return func(context.Context, *Pack) (string, error) { staged++; return "", nil }
+		},
+	}
+
+	instr, tools, err := act.ActivateSkillPacks(ctx, []string{"alpha"}, "run1", "agent1")
+	if err != nil {
+		t.Fatal(err)
+	}
+	if instr == "" {
+		t.Error("expected catalog instructions")
+	}
+	found := false
+	for _, tl := range tools {
+		if tl.Name == "skill_use" {
+			found = true
+		}
+	}
+	if !found {
+		t.Errorf("expected a skill_use tool, got %d tools", len(tools))
+	}
+
+	// unknown name → nothing resolves (no error, no tools).
+	if in, tl, err := act.ActivateSkillPacks(ctx, []string{"nope"}, "r", "a"); err != nil || in != "" || tl != nil {
+		t.Fatalf("unknown pack should resolve to nothing: in=%q tools=%v err=%v", in, tl, err)
+	}
+
+	// nil-safe: a zero Activator (or empty names) is inert.
+	if in, tl, err := (&Activator{}).ActivateSkillPacks(ctx, []string{"alpha"}, "r", "a"); err != nil || in != "" || tl != nil {
+		t.Fatalf("zero Activator should be inert: %q %v %v", in, tl, err)
+	}
+}