vigiles 5.1.0 → 5.2.0

package/README.md

@@ -138,8 +138,8 @@ That's why you can eval your harness on every change, not just once.
 ## More
 
 - **[Plugin health leaderboard →](docs/cli.md#scan-dir)** — point `scan` at a marketplace (e.g. `wshobson/agents`) and it ranks every plugin by structural health (0–100, A–F), worst issues first — still **no key**. Add `--trigger` for the model-gated column: do the skills actually fire?
-- **[CLI & GitHub Action →](docs/cli.md)** — every command, the Action (inputs / output / versioning), the Claude Code plugin, and the `lint` rules.
-- **[Skills →](docs/skills.md)** — consumer skills installed as a Claude Code plugin: `/plugin marketplace add zernie/vigiles` then `/plugin install vigiles@vigiles` (or let `vigiles init` do it). The model-invocable ones (`test-harness`, `strengthen`, `edit-spec`) fire on their own — ask _"test my skills"_, _"strengthen my rules"_, or _"add a rule to CLAUDE.md"_ and the agent reaches for them; `migrate-to-spec` and `linter-docs` are user-invoked.
+- **[CLI & GitHub Action →](docs/cli.md)** — every command, the Action (inputs / output / versioning), and the Claude Code plugin. The full **[lint rules matrix →](docs/verifying-instruction-files.md#the-validation-rules--the-full-matrix)** lives with the linting guide.
+- **[Skills →](docs/skills.md)** — consumer skills installed as a Claude Code plugin: `/plugin marketplace add zernie/vigiles` then `/plugin install vigiles@vigiles` (or let `vigiles init` do it). The model-invocable ones (`test-harness`, `strengthen`, `edit-spec`) fire on their own — ask _"test my skills"_, _"strengthen my rules"_, or _"add a rule to CLAUDE.md"_ and the agent reaches for them; `adopt-spec` and `linter-docs` are user-invoked.
 - **[Docs index →](docs/README.md)** · **[Research →](research/README.md)** · **[Related tools →](docs/related-tools.md)** (ast-grep, Dependency Cruiser, Ruler, rulesync).
 - Companion to [Feedback Loop Is All You Need](https://zernie.com/blog/feedback-loop-is-all-you-need).
 

package/dist/adapters/claude-code/adapter.js

@@ -23,6 +23,7 @@ exports.claudeCodeAdapter = {
         referenceVerification: true,
         harnessTesting: true,
         shellHooks: true,
+        subagents: true,
     },
     dialect: dialect_js_1.claudeCodeDialect,
     layout: layout_js_1.claudeCodeLayout,

package/dist/adapters/claude-code/agent-runtime.d.ts

@@ -22,6 +22,7 @@
  * (mirrors `.vigiles/active-skill.json`). The decision logic below is
  * harness-agnostic and fully testable.
  */
+import type { PurityLevel } from "../../core/effects.js";
 /**
  * Parse an agent's allowed-tools contract from its compiled markdown.
  *
@@ -41,6 +42,14 @@ export declare function parseAgentTools(markdown: string): string[] | null;
  * rail (`tools:`) and the `disallowed-tools-contract` scan/lint.
  */
 export declare function parseAgentToolList(markdown: string, key: string): string[] | null;
+/**
+ * Parse the declared purity floor from a compiled agent's `.md` — the
+ * `<!-- vigiles:purity:LEVEL -->` marker `compile` emits (see `purityMarker`).
+ * Returns null when no marker is present (the unit declared no floor, so the
+ * purity gate imposes no constraint). The single source of truth the runtime
+ * gate reads, exactly like `tools:` for the tool-contract rail.
+ */
+export declare function parseAgentPurity(markdown: string): PurityLevel | null;
 export interface PreToolDecision {
     /** Whether the tool call is allowed (true) or blocked (false). */
     readonly allow: boolean;
@@ -64,11 +73,16 @@ export declare function clearActiveAgent(cwd: string): void;
 /** The path of the active agent's compiled `.md`, or null when none is active. */
 export declare function readActiveAgent(cwd: string): string | null;
 /**
- * PreToolUse-hook decision. If an agent is active, parse its compiled `.md`
- * tool contract and allow the call only when the tool is in the allowlist;
- * otherwise block and tell the model which tools it may use. With no active
- * agent (or an agent that inherits all tools), always allow — the rail only
- * constrains agents that declared a contract.
+ * PreToolUse-hook decision. If an agent is active, enforce BOTH deterministic
+ * rails its compiled `.md` declares, in order:
+ *
+ *  1. the tool-contract rail (`tools:`) — allow only listed tools;
+ *  2. the purity gate (`vigiles:purity:`) — allow only calls within the declared
+ *     effect floor, refining `Bash` by the live `command` (`decidePurityGate`).
+ *
+ * The first to deny wins, feeding its reason back to the model. With no active
+ * agent (or one that declared neither contract), always allow — the rails only
+ * constrain agents that opted in.
  */
-export declare function evaluatePreToolUse(cwd: string, tool: string): PreToolDecision;
+export declare function evaluatePreToolUse(cwd: string, tool: string, command?: string): PreToolDecision;
 //# sourceMappingURL=agent-runtime.d.ts.map

package/dist/adapters/claude-code/agent-runtime.js

@@ -26,6 +26,7 @@
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.parseAgentTools = parseAgentTools;
 exports.parseAgentToolList = parseAgentToolList;
+exports.parseAgentPurity = parseAgentPurity;
 exports.decidePreToolUse = decidePreToolUse;
 exports.setActiveAgent = setActiveAgent;
 exports.clearActiveAgent = clearActiveAgent;
@@ -34,6 +35,9 @@ exports.evaluatePreToolUse = evaluatePreToolUse;
 const node_fs_1 = require("node:fs");
 const node_path_1 = require("node:path");
 const frontmatter_read_js_1 = require("../../core/frontmatter-read.js");
+const effects_js_1 = require("../../core/effects.js");
+const dialect_js_1 = require("./dialect.js");
+const effect_region_js_1 = require("./effect-region.js");
 // ---------------------------------------------------------------------------
 // Parse the tool contract from a compiled agent .md
 // ---------------------------------------------------------------------------
@@ -60,6 +64,18 @@ function parseAgentTools(markdown) {
 function parseAgentToolList(markdown, key) {
     return (0, frontmatter_read_js_1.frontmatterList)((0, frontmatter_read_js_1.readFrontmatter)(markdown), key);
 }
+const PURITY_RE = /<!--\s*vigiles:purity:(pure|bounded|unrestricted)\s*-->/;
+/**
+ * Parse the declared purity floor from a compiled agent's `.md` — the
+ * `<!-- vigiles:purity:LEVEL -->` marker `compile` emits (see `purityMarker`).
+ * Returns null when no marker is present (the unit declared no floor, so the
+ * purity gate imposes no constraint). The single source of truth the runtime
+ * gate reads, exactly like `tools:` for the tool-contract rail.
+ */
+function parseAgentPurity(markdown) {
+    const m = PURITY_RE.exec(markdown);
+    return m ? m[1] : null;
+}
 /**
  * Decide whether `tool` is allowed under an agent's tool contract. Pure, so the
  * rail is unit-testable without spawning anything.
@@ -114,20 +130,47 @@ function readActiveAgent(cwd) {
 // PreToolUse-hook decision
 // ---------------------------------------------------------------------------
 /**
- * PreToolUse-hook decision. If an agent is active, parse its compiled `.md`
- * tool contract and allow the call only when the tool is in the allowlist;
- * otherwise block and tell the model which tools it may use. With no active
- * agent (or an agent that inherits all tools), always allow — the rail only
- * constrains agents that declared a contract.
+ * PreToolUse-hook decision. If an agent is active, enforce BOTH deterministic
+ * rails its compiled `.md` declares, in order:
+ *
+ *  1. the tool-contract rail (`tools:`) — allow only listed tools;
+ *  2. the purity gate (`vigiles:purity:`) — allow only calls within the declared
+ *     effect floor, refining `Bash` by the live `command` (`decidePurityGate`).
+ *
+ * The first to deny wins, feeding its reason back to the model. With no active
+ * agent (or one that declared neither contract), always allow — the rails only
+ * constrain agents that opted in.
  */
-function evaluatePreToolUse(cwd, tool) {
+function evaluatePreToolUse(cwd, tool, command) {
     const agentPath = readActiveAgent(cwd);
     if (!agentPath)
         return { allow: true, message: "" };
     const full = (0, node_path_1.resolve)(cwd, agentPath);
     if (!(0, node_fs_1.existsSync)(full))
         return { allow: true, message: "" };
-    const allowed = parseAgentTools((0, node_fs_1.readFileSync)(full, "utf-8"));
-    return decidePreToolUse(allowed, tool);
+    const md = (0, node_fs_1.readFileSync)(full, "utf-8");
+    // 1) Tool-contract rail — the declared allowlist.
+    const rail = decidePreToolUse(parseAgentTools(md), tool);
+    if (!rail.allow)
+        return rail;
+    // 2) Purity gate — the declared effect floor, refined by the live command.
+    //    If an effect boundary is declared, tighten to "pure" outside it and apply
+    //    the declared purity (or "unrestricted") inside.
+    const purity = parseAgentPurity(md);
+    const boundary = (0, effect_region_js_1.hasEffectBoundary)(md);
+    if (boundary) {
+        const effective = (0, effect_region_js_1.readEffectActive)(cwd)
+            ? (purity ?? "unrestricted")
+            : "pure";
+        const gate = (0, effects_js_1.decidePurityGate)(effective, tool, command, dialect_js_1.claudeCodeDialect);
+        if (!gate.allow)
+            return gate;
+    }
+    else if (purity) {
+        const gate = (0, effects_js_1.decidePurityGate)(purity, tool, command, dialect_js_1.claudeCodeDialect);
+        if (!gate.allow)
+            return gate;
+    }
+    return { allow: true, message: "" };
 }
 //# sourceMappingURL=agent-runtime.js.map

package/dist/adapters/claude-code/dialect.js

@@ -63,5 +63,24 @@ exports.claudeCodeDialect = {
     // Claude Code reads the full SKILL.md frontmatter set (description,
     // disable-model-invocation, argument-hint, …).
     skillFrontmatter: "claude-code",
+    // Tools that produce side effects in Claude Code. The complement — the
+    // read-only tools — are: Read, Grep, Glob, LS, ToolSearch (and LSP/Agent
+    // which are not in the subagent catalog). Bash is side-effecting because
+    // `cat` and `rm -rf` are the same tool at the tool-name level — the
+    // sandbox is the only closure for subprocess effects.
+    sideEffectingTools: [
+        "Bash",
+        "BashOutput",
+        "KillBash",
+        "Edit",
+        "MultiEdit",
+        "Write",
+        "NotebookEdit",
+        "WebFetch",
+        "WebSearch",
+        "Skill",
+        "Task",
+        "TodoWrite",
+    ],
 };
 //# sourceMappingURL=dialect.js.map

package/dist/adapters/claude-code/effect-region.d.ts

@@ -0,0 +1,9 @@
+/** Record that the agent has entered an effect boundary. */
+export declare function setEffectActive(cwd: string): void;
+/** Clear the effect-active marker (the agent exited the effect boundary). */
+export declare function clearEffectActive(cwd: string): void;
+/** True iff the agent is currently inside an effect boundary. Tolerates malformed file. */
+export declare function readEffectActive(cwd: string): boolean;
+/** True iff the compiled markdown declares an effect boundary (`<!-- vigiles:effect -->`). */
+export declare function hasEffectBoundary(markdown: string): boolean;
+//# sourceMappingURL=effect-region.d.ts.map

package/dist/adapters/claude-code/effect-region.js

@@ -0,0 +1,45 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.setEffectActive = setEffectActive;
+exports.clearEffectActive = clearEffectActive;
+exports.readEffectActive = readEffectActive;
+exports.hasEffectBoundary = hasEffectBoundary;
+/**
+ * Effect-boundary position-aware state tracking.
+ * Mirrors active-unit tracking (.vigiles/active-agent.json / .vigiles/active-skill.json).
+ * The PreToolUse hook reads this file to decide whether the agent is inside an
+ * effect boundary (set by `vigiles effect-enter`) or outside it.
+ */
+const node_fs_1 = require("node:fs");
+const node_path_1 = require("node:path");
+const EFFECT_ACTIVE_PATH = ".vigiles/effect-active.json";
+/** Record that the agent has entered an effect boundary. */
+function setEffectActive(cwd) {
+    const p = (0, node_path_1.resolve)(cwd, EFFECT_ACTIVE_PATH);
+    (0, node_fs_1.mkdirSync)((0, node_path_1.dirname)(p), { recursive: true });
+    (0, node_fs_1.writeFileSync)(p, JSON.stringify({ active: true }) + "\n");
+}
+/** Clear the effect-active marker (the agent exited the effect boundary). */
+function clearEffectActive(cwd) {
+    const p = (0, node_path_1.resolve)(cwd, EFFECT_ACTIVE_PATH);
+    if ((0, node_fs_1.existsSync)(p))
+        (0, node_fs_1.rmSync)(p);
+}
+/** True iff the agent is currently inside an effect boundary. Tolerates malformed file. */
+function readEffectActive(cwd) {
+    const p = (0, node_path_1.resolve)(cwd, EFFECT_ACTIVE_PATH);
+    if (!(0, node_fs_1.existsSync)(p))
+        return false;
+    try {
+        const parsed = JSON.parse((0, node_fs_1.readFileSync)(p, "utf-8"));
+        return parsed.active === true;
+    }
+    catch {
+        return false;
+    }
+}
+/** True iff the compiled markdown declares an effect boundary (`<!-- vigiles:effect -->`). */
+function hasEffectBoundary(markdown) {
+    return markdown.includes("<!-- vigiles:effect -->");
+}
+//# sourceMappingURL=effect-region.js.map

package/dist/adapters/claude-code/layout.js

@@ -9,6 +9,9 @@ exports.claudeCodeLayout = {
     settingsFormat: "json",
     instructionFile: "CLAUDE.md",
     surfaceDirs: ["skills", "agents", "commands"],
+    skillDir: "skills",
+    agentDir: "agents",
+    commandDir: "commands",
     materializeRoot: ".claude",
     pluginRootToken: "${CLAUDE_PLUGIN_ROOT}",
     mcpConfigFile: ".mcp.json",

package/dist/adapters/claude-code/skill-runtime.d.ts

@@ -20,6 +20,7 @@
  * (`vigiles run-skill`). It is not a silent hook and runs nothing the spec
  * didn't declare as a gate.
  */
+import type { PurityLevel } from "../../core/effects.js";
 export type RuntimeGate = {
     readonly kind: "cmd";
     readonly command: string;
@@ -86,6 +87,30 @@ export declare function setActiveSkill(cwd: string, skillPath: string): void;
 export declare function clearActiveSkill(cwd: string): void;
 /** The path of the active skill, or null when none is in progress. */
 export declare function readActiveSkill(cwd: string): string | null;
+/**
+ * Parse the declared purity floor from a compiled SKILL.md — the
+ * `<!-- vigiles:purity:LEVEL -->` marker `compileSkill` emits (see
+ * `purityMarker` in compile.ts). Returns null when no marker is present (the
+ * skill declared no floor, so the purity gate imposes no constraint). Mirrors
+ * `parseAgentPurity` in agent-runtime.ts.
+ */
+export declare function parseSkillPurity(markdown: string): PurityLevel | null;
+/** A runtime allow/deny decision (mirrors PreToolDecision in agent-runtime.ts). */
+export interface SkillPreToolDecision {
+    /** Whether the tool call is allowed (true) or blocked (false). */
+    readonly allow: boolean;
+    /** Message fed back to the model on a block; empty on allow. */
+    readonly message: string;
+}
+/**
+ * PreToolUse purity gate for skills. Mirrors `evaluatePreToolUse` in
+ * agent-runtime.ts, but enforces ONLY the purity floor — skills have no
+ * tools-allowlist rail (that's a separate, future concern). If a skill is
+ * active and declares a `vigiles:purity:` marker, `decidePurityGate` checks
+ * the live call (refining `Bash` by the concrete command via `isReadOnlyBash`).
+ * With no active skill, a missing `.md`, or no purity marker, always allows.
+ */
+export declare function evaluateSkillPreToolUse(cwd: string, tool: string, command?: string): SkillPreToolDecision;
 export interface StopDecision {
     /** Whether the agent may stop (true) or must keep working (false). */
     readonly allow: boolean;

package/dist/adapters/claude-code/skill-runtime.js

@@ -30,10 +30,15 @@ exports.runSkillGates = runSkillGates;
 exports.setActiveSkill = setActiveSkill;
 exports.clearActiveSkill = clearActiveSkill;
 exports.readActiveSkill = readActiveSkill;
+exports.parseSkillPurity = parseSkillPurity;
+exports.evaluateSkillPreToolUse = evaluateSkillPreToolUse;
 exports.evaluateStopHook = evaluateStopHook;
 const node_child_process_1 = require("node:child_process");
 const node_fs_1 = require("node:fs");
 const node_path_1 = require("node:path");
+const effects_js_1 = require("../../core/effects.js");
+const dialect_js_1 = require("./dialect.js");
+const effect_region_js_1 = require("./effect-region.js");
 const STEP_RE = /^###\s+Step\s+(\d+)/;
 const GATE_CMD_RE = /<!--\s*vigiles:gate\s+"([^"]*)"(?:\s+retry:(\d+))?\s*-->/;
 const GATE_FILE_RE = /<!--\s*vigiles:gate\s+file:(\S+)\s*-->/;
@@ -257,6 +262,49 @@ function readActiveSkill(cwd) {
         return null;
     }
 }
+// ---------------------------------------------------------------------------
+// Skill purity gate (mirrors agent-runtime.ts parseAgentPurity / evaluatePreToolUse)
+// ---------------------------------------------------------------------------
+const PURITY_RE = /<!--\s*vigiles:purity:(pure|bounded|unrestricted)\s*-->/;
+/**
+ * Parse the declared purity floor from a compiled SKILL.md — the
+ * `<!-- vigiles:purity:LEVEL -->` marker `compileSkill` emits (see
+ * `purityMarker` in compile.ts). Returns null when no marker is present (the
+ * skill declared no floor, so the purity gate imposes no constraint). Mirrors
+ * `parseAgentPurity` in agent-runtime.ts.
+ */
+function parseSkillPurity(markdown) {
+    const m = PURITY_RE.exec(markdown);
+    return m ? m[1] : null;
+}
+/**
+ * PreToolUse purity gate for skills. Mirrors `evaluatePreToolUse` in
+ * agent-runtime.ts, but enforces ONLY the purity floor — skills have no
+ * tools-allowlist rail (that's a separate, future concern). If a skill is
+ * active and declares a `vigiles:purity:` marker, `decidePurityGate` checks
+ * the live call (refining `Bash` by the concrete command via `isReadOnlyBash`).
+ * With no active skill, a missing `.md`, or no purity marker, always allows.
+ */
+function evaluateSkillPreToolUse(cwd, tool, command) {
+    const skillPath = readActiveSkill(cwd);
+    if (!skillPath)
+        return { allow: true, message: "" };
+    const full = (0, node_path_1.resolve)(cwd, skillPath);
+    if (!(0, node_fs_1.existsSync)(full))
+        return { allow: true, message: "" };
+    const md = (0, node_fs_1.readFileSync)(full, "utf-8");
+    const purity = parseSkillPurity(md);
+    const boundary = (0, effect_region_js_1.hasEffectBoundary)(md);
+    if (boundary) {
+        const effective = (0, effect_region_js_1.readEffectActive)(cwd)
+            ? (purity ?? "unrestricted")
+            : "pure";
+        return (0, effects_js_1.decidePurityGate)(effective, tool, command, dialect_js_1.claudeCodeDialect);
+    }
+    if (!purity)
+        return { allow: true, message: "" };
+    return (0, effects_js_1.decidePurityGate)(purity, tool, command, dialect_js_1.claudeCodeDialect);
+}
 /**
  * Stop-hook decision. If a skill is active and declares a result gate, run it:
  * allow the stop only when the gate passes; otherwise block and tell the model

package/dist/adapters/codex/adapter.js

@@ -29,6 +29,9 @@ exports.codexAdapter = {
         referenceVerification: true,
         harnessTesting: true,
         shellHooks: true,
+        // Codex `[agents]` is a concurrency table, not a subagent tool-contract file
+        // — the subagent-surface rules report n/a here (a deliberate non-goal).
+        subagents: false,
     },
     dialect: dialect_js_1.codexDialect,
     layout: layout_js_1.codexLayout,

package/dist/adapters/codex/layout.js

@@ -9,6 +9,9 @@ exports.codexLayout = {
     settingsFormat: "toml",
     instructionFile: "AGENTS.md",
     surfaceDirs: ["skills", "prompts"],
+    skillDir: "skills",
+    agentDir: "", // Codex `[agents]` is a TOML concurrency table, not a subagent dir
+    commandDir: "prompts",
     materializeRoot: ".codex",
     pluginRootToken: "${PLUGIN_ROOT}",
     mcpConfigFile: ".mcp.json",

package/dist/adapters/opencode/adapter.js

@@ -29,6 +29,7 @@ exports.opencodeAdapter = {
         referenceVerification: true,
         harnessTesting: true,
         shellHooks: false,
+        subagents: true,
     },
     dialect: dialect_js_1.opencodeDialect,
     layout: layout_js_1.opencodeLayout,

package/dist/adapters/opencode/layout.js

@@ -16,6 +16,9 @@ exports.opencodeLayout = {
     // `.opencode/` segment. (Contrast Claude Code: root-level `skills/` surfaces
     // relocated under `.claude`.)
     surfaceDirs: [".opencode/agent", ".opencode/command"],
+    skillDir: ".opencode/skill",
+    agentDir: ".opencode/agent",
+    commandDir: ".opencode/command",
     materializeRoot: "",
     pluginRootToken: "${OPENCODE_PLUGIN_ROOT}",
     mcpConfigFile: "opencode.json",

package/dist/check.d.ts

@@ -104,6 +104,14 @@ export declare function turns(opts: {
 }): Check<Trace>;
 /** The agent wrote (or left) a file at this path in the work dir. */
 export declare function wrote(path: string): Check<Trace>;
+/**
+ * The agent did NOT leave a file at this path — the **side-effect boundary**
+ * negative: a skill that declares it writes only `out.txt` should leave nothing
+ * at `secrets.env`. The symmetric sibling of `wrote()`; pairs with
+ * `notTool(...)` to assert a unit stayed inside its declared write surface
+ * deterministically (no model judge).
+ */
+export declare function didNotWrite(path: string): Check<Trace>;
 /** The named subagent (`Task` `subagent_type`) ran and passed every nested check. */
 export declare function subagent(name: string, checks: readonly Check<Trace>[]): Check<Trace>;
 /** The hook blocked the event (exit 2 / deny / block). */

package/dist/check.js

@@ -11,6 +11,7 @@ exports.hookFired = hookFired;
 exports.received = received;
 exports.turns = turns;
 exports.wrote = wrote;
+exports.didNotWrite = didNotWrite;
 exports.subagent = subagent;
 exports.blocked = blocked;
 exports.allowed = allowed;
@@ -236,16 +237,34 @@ function wrote(path) {
         toJSON: () => ({ kind: "wrote", path }),
     };
 }
+/**
+ * The agent did NOT leave a file at this path — the **side-effect boundary**
+ * negative: a skill that declares it writes only `out.txt` should leave nothing
+ * at `secrets.env`. The symmetric sibling of `wrote()`; pairs with
+ * `notTool(...)` to assert a unit stayed inside its declared write surface
+ * deterministically (no model judge).
+ */
+function didNotWrite(path) {
+    return {
+        kind: "didNotWrite",
+        eval: (t) => t.file(path) === null
+            ? ok(`file "${path}" was not created`)
+            : no(`expected the agent NOT to create "${path}", but it exists`),
+        toJSON: () => ({ kind: "didNotWrite", path }),
+    };
+}
 // ---------------------------------------------------------------------------
 // Subagent — a `Task` run as a nested trace. Run checks over what the SUBAGENT
 // did, not just that `Task` fired. Composes the whole vocabulary recursively.
 // ---------------------------------------------------------------------------
-/** Wrap a subagent's tool calls as a minimal `Trace` so checks run over it. */
+/** Wrap a subagent's tool calls + returned text as a minimal `Trace` so checks
+ * (incl. `output()` over the sub's RETURN — where a result() vigiles:ok/err block
+ * lands) run over it. */
 function subTrace(sub) {
     return {
         toolCalls: sub.toolCalls,
         hooks: [],
-        output: "",
+        output: sub.output,
         modelRequests: [],
         turns: 0,
         subagents: [],
@@ -258,7 +277,12 @@ function subagent(name, checks) {
         kind: "subagent",
         eval: (t) => {
             const subs = t.subagents ?? [];
-            const sub = subs.find((s) => s.name === name);
+            // A `--plugin-dir` agent's `subagent_type` is namespaced `plugin:agent`
+            // (e.g. "reviewer-spec:code-reviewer"), but callers pass the bare agent name
+            // — so match the full id OR its last `:`-segment. Non-namespaced (harness
+            // mock) names match exactly as before.
+            const bare = (n) => n.includes(":") ? n.slice(n.lastIndexOf(":") + 1) : n;
+            const sub = subs.find((s) => s.name === name || bare(s.name) === name);
             if (!sub) {
                 return no(`expected subagent "${name}" to run; subagents that ran: ${subs.length > 0 ? `[${subs.map((s) => s.name).join(", ")}]` : "none"}`);
             }