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 skills/stoa-platform/stoa/ci-debugnpx skills add stoa-platform/stoa --skill ci-debuggit 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 | $0.00028 | $0.00881 |
| Opus 5 | $0.00014 | $0.00441 |
| Sonnet 5 | $0.00006 | $0.00176 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
ci-debug 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CI Debug — Analyse des echecs CI
Contexte dynamique
- Checks PR en cours: !
gh pr checks 2>/dev/null | head -20 - Workflows recents: !
gh run list --limit 5 --json name,status,conclusion,headBranch --template '{{range .}}{{.name}} | {{.status}} | {{.conclusion}} | {{.headBranch}}{{"\n"}}{{end}}' 2>/dev/null
Instructions
Analyser l'echec CI pour: $ARGUMENTS
Step 1: Identifier le workflow en echec
Si c'est un numero de PR:
gh pr checks $0
gh run list --branch $(gh pr view $0 --json headRefName -q .headRefName) --limit 3
Si c'est une URL de workflow run:
gh run view $0 --log-failed
Step 2: Extraire les logs d'erreur
gh run view <run-id> --log-failed 2>&1 | head -100
Chercher les patterns:
error,Error,ERRORFAIL,FAILEDexit code 1,exit code 2denied,forbidden,unauthorized
Step 3: Diagnostiquer
Causes frequentes dans STOA CI:
| Pipeline | Erreur frequente | Cause | Fix |
|---|---|---|---|
| Python CI | I001 import order |
isort non respecte | ruff check --fix |
| Python CI | mypy type error |
Type hints manquants | Ajouter les annotations |
| Node CI | vitest fail |
Mock MSW manquant | Ajouter handler MSW |
| Node CI | eslint warnings |
Max warnings depassé (0 pour UI, 20 pour portal) | Fixer les warnings |
| Docker | buildx fail |
Cache layer miss ou multi-arch | Verifier --platform linux/amd64,linux/arm64 |
| Helm | helm lint fail |
Values manquantes, indentation | Verifier values.yaml |
| Security | dependency-review |
GitHub Advanced Security non active | Connu, non-bloquant |
| K8s deploy | kubectl apply fail |
Selector immutable, Kyverno block | Voir .claude/docs/k8s-deploy.md |
| K8s deploy | rollout timeout |
maxSurge/maxUnavailable deadlock | maxUnavailable: 1, maxSurge: 0 |
Step 4: Proposer le fix
Pour chaque erreur identifiee:
- Fichier exact a modifier (chemin complet)
- Diff propose (old → new)
- Commande de verification locale
- Impact sur les autres workflows
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 · 101 lines · 28 tokens per session scan A 76496348541e
ci-debug is a skill published in the GitHub repository stoa-platform/stoa (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 881 once invoked, about $0.0001 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 skills, from other repositories
lyrik
Security assessment of a codebase — minimal mode for runner validation.
librarian
Read-only retrieval over the daily-digest kept set. Slash-invoke with /librarian ; returns items verbatim with citations.
notes
Create and manage text notes in the workspace.
tdx-assets
Look up staff devices, assets, and locations in TeamDynamix (TDX). Given a list of names, emails, or partial identifiers, resolve each person and return the assets assigned to them with location, model, ownership type, and status. Read-only.
aggregator
Daily fetch from a fixed public allowlist; score against the user's interests file; cluster into themes; push the digest to the configured channel.
csv-tools
Parse and analyze CSV data.