Référence
Travailleurs délégués
Travailleurs délégués persistants pour la recherche, l'audit, la qualité et l'orchestration, avec contrats de frontmatter et protocoles d'isolation de déploiement.
Les travailleurs délégués persistants vivent sous forme de fichiers plats dans le
répertoire canonique des travailleurs délégués, avec le suffixe <name>.md. Le
chemin canonique est :
src/apothem/agents/Chaque travailleur délégué est un rôle de recherche, d'audit, de qualité ou d'orchestration, doté de ses propres restrictions d'outils et de son propre prompt système.
| Travailleur délégué | Fichier | Motif | Politique de modèle |
|---|---|---|---|
| Codebase Explorer | voir le chemin du manifeste ci-dessous | Recherche | sélectionné par l'hôte |
| Convention Auditor | voir le chemin du manifeste ci-dessous | Audit | sélectionné par l'hôte |
| Quality Gate | voir le chemin du manifeste ci-dessous | Qualité | sélectionné par l'hôte |
| Memory Auditor | voir le chemin du manifeste ci-dessous | Audit | sélectionné par l'hôte |
Chemins canoniques du manifeste :
src/apothem/agents/codebase-explorer.md
src/apothem/agents/convention-auditor.md
src/apothem/agents/quality-gate.md
src/apothem/agents/memory-auditor.mdContrat de frontmatter
---
name: <agent name>
version: <semver>
updated: <YYYY-MM-DD>
description: <one-line role>
tools: <comma-separated tool list>
disallowedTools: <comma-separated deny list>
maxTurns: <integer>
---Orchestration
Le déploiement des travailleurs délégués, le protocole de lancement en parallèle, l'application du contrat de retour et la discipline d'isolation vivent dans la règle d'orchestration. L'arbre de répartition par travailleur vit dans la règle des motifs d'orchestration, §Decision Tree. Chemins canoniques :
src/apothem/rules/agent-orchestration.md
src/apothem/rules/agent-orchestration-patterns.mdInventaire généré des travailleurs délégués
| Name | Description | Source |
|---|---|---|
README | Persistent agent definitions — the reusable sub-agent specifications the harness materializes whenever the orchestrator deploys a research, audit, or quality team. Each agent is a | src/apothem/agents/README.md |
codebase-explorer | Read-only codebase exploration — exhaustively find every instance of a pattern, trace call/import dependencies, discover host conventions, map architecture and layering. Use when the query is 'where is X used', 'find all callers of Y', 'what convention does this repo follow for Z', 'map the module structure', or 'trace what depends on this file' — never for edits, never for design. Works through Grep / Glob / Read plus read-only Bash and returns evidence-cited findings (path + line + snippet) exhaustive within the declared scope; reports gaps rather than guessing. | src/apothem/agents/codebase-explorer.md |
convention-auditor | Read-only conventions auditor: verify naming (kebab-case files, snake_case Python, frontmatter keys), cross-reference resolution (dead rule/skill/agent paths, broken anchors, half-edge bindings), formatting standards (SPDX header presence, frontmatter contract), and ecosystem coherence (orphan artifacts, sibling-convention drift, registry gaps). Dispatch when a change touches multiple rules/skills/agents/commands and you need a binary PASS/FINDING verdict per instance with file+line+expected+actual evidence — e.g. 'audit naming across the harness adapters', 'check every new rule resolves its Bindings cross-refs', 'verify the skills cohort matches the kebab-case + SKILL.md convention'. Read-only: never fixes, never runs shell. Conventions are owned upstream and verified against, never re-derived; every finding cites severity + evidence. | src/apothem/agents/convention-auditor.md |
dependency-auditor | Read-only dependency-tree risk audit — flags unpinned, stale, duplicate, and known-vulnerable dependencies with manifest/lockfile evidence. Use when auditing supply-chain risk, before a release cut, after adding a dependency, or when a CVE/advisory lands. Detects the ecosystem via host-discovery: npm (package.json + package-lock/yarn/pnpm), pip (pyproject/requirements + lock), cargo (Cargo.toml + Cargo.lock), go (go.mod + go.sum). Runs npm audit / pip-audit / cargo audit / govulncheck and returns a risk-ranked table (known-vulnerable → unpinned → duplicate → stale) with per-row evidence; never widens a pin or escalates a scope — gaps surface as inquiry. | src/apothem/agents/dependency-auditor.md |
fact-checker | Read-only adversarial claim verification — decompose input into atomic claims, seek ≥2 independent sources, attempt refutation, assign cited verdicts (supported / refuted / unverifiable) with quoted evidence and confidence. Use when a claim needs proof before it ships: a benchmark or statistic in docs/copy, a 'X is faster/safer than Y' assertion, a citation that names an RFC or spec, a release note, or any factual claim a reviewer would challenge. Routes external claims through WebSearch / WebFetch and repository claims through Read / Glob / Grep; defaults to refuted-or-unverifiable when evidence is insufficient, never a charitable supported. | src/apothem/agents/fact-checker.md |
mcp-builder | Scaffold a Model Context Protocol (MCP) server skeleton from a tool/resource contract — contract-first, well-typed tools, minimal surface. Use when: 'build an MCP server for <API>', 'scaffold MCP tools from this spec', 'wire FastMCP/TypeScript-SDK tool definitions', 'add a tool that exposes <resource> over MCP'. Detection: tool names + argument shapes + return types + resource URIs are stated or derivable. Selects the SDK via host-discovery (FastMCP for Python, the TypeScript SDK for Node), emits one typed tool definition per contract entry plus a list-tools smoke test, and scaffolds nothing speculative. Not for: tuning, securing, or load-testing an existing server (those surface as adjacent gaps). | src/apothem/agents/mcp-builder.md |
memory-auditor | Read-only memory-file auditor: cross-reference every claim in the harness memory tier (MEMORY.md index + topic files under <harness-root>/projects/{hash}/memory/ and <harness-root>/memory/) against actual filesystem state — file/line/rule counts (glob and count), referenced paths (do they exist?), rule scope labels (match pathFilter frontmatter?), dates (against frontmatter updated: or mtime, never the system clock), and cross-reference matrices. Dispatch when MEMORY.md or a topic file may have drifted from reality and you need a per-claim PASS/FAIL verdict with contradicting evidence — e.g. 'audit MEMORY.md after the rules cohort was renamed', 'verify the memory index counts match the current ecosystem', 'check the debugging topic file for stale references to deleted artifacts'. Existence + name match only; never re-audit an artifact's internal correctness (convention-auditor's scope). Read-only: never writes, never fixes. | src/apothem/agents/memory-auditor.md |
prompt-evaluator | Read-only rubric scoring of a prompt's output set — score each output against each named criterion (PASS/FAIL with cited evidence), aggregate per-criterion pass-rate, flag regressions against a baseline, and name recurring failure modes. Use when prompt or model outputs need a reproducible verdict before they ship: comparing a reprompted variant against the prior version, gating a system-prompt change, judging an LLM-as-judge eval set, scoring few-shot outputs against acceptance criteria, or proving a quality claim a reviewer would challenge. Requires an explicit rubric — an absent or underspecified rubric blocks scoring and routes as inquiry; never invents a criterion or threshold, never scores charitably. | src/apothem/agents/prompt-evaluator.md |
quality-gate | Read-only quality-gate runner — discovers the host's lint / type-check / test / security / build commands, runs them in the correct order (build → type-check → tests+lint+security in parallel), and returns a per-gate PASS/FAIL verdict with file+line+error evidence. Reports, never fixes. Dispatch as a Quality team before a release cut, after a multi-file change, or to confirm a fix is green — e.g. 'run the full quality matrix and tell me what fails', 'gate this branch before I push', 'is the test suite green and the types clean?'. Detects tooling via host-discovery (ruff/eslint/markdownlint, mypy/tsc/pyright, pytest/jest/cargo test/go test, bandit/npm audit/gitleaks); never assumes a stack. | src/apothem/agents/quality-gate.md |
refactor-surgeon | Scoped, behavior-preserving refactor of a named target — extract the behavioral contract, re-derive clean-room (never edit in place), name the one deficiency removed, verify regression via the host's own tests. Dispatch on a single named target with a clear refactor intent — e.g. 'extract the duplicated validation in src/apothem/cli/install.py into a helper', 'untangle the nested conditionals in materializer.py without changing output', 'rename the god-object methods in adapter.py to reveal intent'. Touches only the named target; adjacent gaps surface as findings, never as edits. Behavior, contracts, and side effects are identical before and after; a behavior change is a defect. | src/apothem/agents/refactor-surgeon.md |
research-scout | Read-only source discovery and ranking — decompose a research question into facets, fan out parallel web queries, rank candidates by authority, recency, and relevance, and return a deduplicated ranked source list. Use when a question needs sources before it can be answered: 'find the authoritative spec/RFC for X', 'what are the primary sources on Y', 'gather current references for a docs/copy claim', 'survey the landscape before a deep dive'. Fans external facets through WebSearch / WebFetch and any in-repo corpus through Read / Glob / Grep. Discovery and ranking only — never fabricates a URL, never synthesizes; claim verification and combination route to the fact-checker / source-synthesis surface. | src/apothem/agents/research-scout.md |
security-scanner | Read-only secret, SAST-pattern, and config-risk sweep — a coarse first-pass that surfaces candidates fast and routes deep scanning to the host's CI scanners. Use when a security review is requested, before a release cut, after touching auth/crypto/IO surfaces, or when a secret may have been committed. Greps for credential literals (key/token/password/private-key/certificate, committed .env values), injection surfaces (shell=True on untrusted input, string-formatted SQL, command interpolation), unsafe-eval (eval/exec/Invoke-Expression), unsafe deserialization (pickle.loads, yaml.load without SafeLoader), and config risk (over-broad CI permissions:, unpinned Actions uses:, network egress). Routes known-vulnerable dependencies to the dependency-auditor agent, CVE/advisory triage to the vuln-triage skill, and leaked-credential rotation to the secret-rotation skill. | src/apothem/agents/security-scanner.md |
test-runner | Read-only test-suite runner — discovers the host's test command, runs it, and triages every failure by root cause with test+file+line+assertion evidence. Reports, never fixes. Dispatch as a Research/Quality team member after a code change, before a release cut, or to confirm a fix is green — e.g. 'run the tests and tell me what's failing and why', 'is the suite green on this branch?', 'triage the failures in the auth module'. Detects the runner via host-discovery (pytest/jest/cargo test/go test/Makefile target from the manifest + CI config); never assumes pytest. | src/apothem/agents/test-runner.md |
Commandes
Définitions de commandes slash mettant en œuvre le pipeline de suite de plan, plus des audits pour la revue du code, de l'architecture, de la sécurité, des dépendances et de la documentation.
Hooks
Gestionnaires d'événements d'outils qui se déclenchent sur SessionStart, PreToolUse et Stop, chargeant des contextes de message imposant l'isolation de git et la discipline des plans.