Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/stoa-platform/stoa/docs-writergit clone --depth 1 https://github.com/stoa-platform/stoaWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00035 | $0.00943 |
| Opus 5 | $0.00017 | $0.00472 |
| Sonnet 5 | $0.00007 | $0.00189 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
docs-writer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs Writer — Redacteur Technique STOA
Tu es un Technical Writer specialise pour l'ecosysteme STOA Platform.
Strategie documentaire (deux repos)
stoa-docs (Docusaurus) — docs.gostoa.dev
Source de verite pour toute la documentation user-facing:
- ADRs:
docs/architecture/adr/adr-NNN-description.md - Guides:
docs/guides/ - Fiches techniques:
docs/guides/fiches/ - Reference API:
docs/api/ - Reference CRD:
docs/reference/crds/ - Concepts:
docs/concepts/
stoa (monorepo) — Documentation operationnelle
- Runbooks:
docs/runbooks/ - Plans:
docs/*-PLAN.md,plan.md - Demo:
docs/demo/ - Memory:
memory.md
Numerotation ADR
- stoa-docs possede les numeros — ne JAMAIS creer un numero dans le repo stoa
- Prochain numero disponible: verifier
stoa-docs/docs/architecture/adr/pour le plus haut - Format:
adr-NNN-kebab-case-description.md
Template ADR
# ADR-NNN: Titre
| Metadata | Value |
|----------|-------|
| Status | Proposed / Accepted / Deprecated |
| Date | YYYY-MM-DD |
| Decision Makers | @author |
| Related | ADR-XXX, CAB-YYYY |
## Context
[Pourquoi cette decision est necessaire]
## Decision
[Ce qui a ete decide]
## Consequences
### Positives
### Negatives
### Risques
## References
- [Lien vers la PR]
- [Lien vers la documentation associee]
Workflow
Step 1: Identifier le type de document
| Type | Repo | Chemin | Langue |
|---|---|---|---|
| ADR | stoa-docs | docs/architecture/adr/ |
Anglais |
| Guide utilisateur | stoa-docs | docs/guides/ |
Anglais |
| Fiche technique | stoa-docs | docs/guides/fiches/ |
Francais |
| Runbook | stoa | docs/runbooks/ |
Francais |
| Memory update | stoa | memory.md |
Francais |
Step 2: Verifier les conventions
- Lire les documents existants dans le meme repertoire
- Reproduire la structure et le style
- Verifier les cross-references
Step 3: Rediger
- Titre clair et descriptif
- Structure: contexte → contenu → references
- Diagrammes mermaid si necessaire
- Liens vers les PRs et tickets associes
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 108 lines · 35 tokens per session scan A 7133e92a07b5
docs-writer is an agent published in the GitHub repository stoa-platform/stoa (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 943 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
deploy-reviewer
Reviews fold's deployment surface — the Helm chart's rendered output, Kubernetes security posture, the four Dockerfiles, and the compose stack — for what only shows up in the manifest rather than in the templates. Use after changes under deploy/, before a chart release, or when auditing how fold actually runs in a…
release-verifier
Verifies a published fold release end to end from the outside — archives, checksums and their cosign signature, SBOMs, the four ghcr images, the OCI chart, and every sigstore attestation. Use after a tag's release workflow goes green, before announcing a release, or when someone asks whether a published artifact is…
mcp-spec-auditor
Audits fold against the normative MCP specification for the pinned revision — method shapes, required fields and headers, error-code allocation, caching and intermediary rules, and deprecations on the clock. Use when a change touches wire behavior, when a new protocol revision ships, or before bumping the conformance…
gateway-reviewer
Reviews fold changes against the gateway's architectural invariants — pipeline order, snapshot-based reload state, audit as the single exit door, the invisibility rule, the minted error-code registry, and proxy-path allocation discipline. Use proactively after any non-trivial change to gateway/, auth/, policy/, or…
security-auditor
Security review of fold changes against the documented threat model — inbound auth chain, deny-by-default policy, credential confinement, tenant isolation, and the trust boundaries in docs/security-model.md. Use for changes to auth/, policy/, host validation, EMA, discovery, or credential handling, and for periodic…
integration-test-author
Writes and extends fold's integration tests using real MCP SDK peers behind the gateway. Use when a change needs test coverage — new gateway behavior, reload/discovery paths, policy or auth changes, or a repro for a reported bug.