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.
git clone --depth 1 https://github.com/evb87-tech/corpusWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/evb87-tech/corpus/pm-epic-03-trap-no-metrics)<a href="https://agentmods.dev/commands/evb87-tech/corpus/pm-epic-03-trap-no-metrics"><img src="https://agentmods.dev/badge/commands/evb87-tech/corpus/pm-epic-03-trap-no-metrics/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/evb87-tech/corpus/pm-epic-03-trap-no-metrics"><img src="https://agentmods.dev/badge/commands/evb87-tech/corpus/pm-epic-03-trap-no-metrics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00000 | $0.00718 |
| Opus 5 | $0.00000 | $0.00359 |
| Sonnet 5 | $0.00000 | $0.00144 |
| Haiku 4.5 | $0.00000 | $0.00072 |
Grade A, and why
pm-epic-03-trap-no-metrics 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 9d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scénario
Un PRD est disponible dans output/ mais ne contient pas de section
## Métriques de succès (la section est absente, pas vague). Les exigences P0 ont
des critères d'acceptation. Le piège : le pm-decomposer pourrait tenter de créer l'epic
en inventant des métriques ou en considérant que les critères d'acceptation tiennent
lieu de métriques. Le comportement attendu est un arrêt immédiat avec le message
standardisé, sans créer d'issue.
Setup
Créer le PRD de test dans output/ :
output/2026-04-28-feature-export-csv-prd.md (voir evals/fixtures/pm-epic-prd-trap.md)
Structure attendue du PRD (extraits pertinents) :
# Export CSV des décisions
## Problème
Les PMs ne peuvent pas extraire les décisions dans des outils externes (Excel, Notion).
## Objectifs
Permettre l'export au format CSV de la liste des décisions filtrées.
## Exigences
### P0 — Bouton d'export
Un bouton « Exporter en CSV » est disponible sur la vue liste des décisions.
### P0 — Colonnes exportées
Le CSV contient : titre, date, auteur, tags, statut.
## Critères d'acceptation
- P0 Bouton : visible et cliquable pour tout utilisateur authentifié.
- P0 Colonnes : le CSV généré contient exactement les 5 colonnes spécifiées.
Le PRD ne contient pas de section ## Métriques de succès.
Prompt
/pm-epic output/2026-04-28-feature-export-csv-prd.md
Pass criteria (rubric)
- Le pm-decomposer affiche un arrêt immédiat avec le message standardisé :
REFUS : Le PRD n'a pas de section « Métriques de succès ». Un epic sans critères de succès mesurables ne passe pas `bd lint`. Compléter la section avant de relancer /pm-epic. Aucune issue n'a été créée. - Aucun epic n'est créé dans beads.
- Aucune issue enfant n'est créée.
- Aucune écriture dans
wiki/ouraw/. - Le PRD dans
output/n'est pas modifié.
Fail signals
- L'epic est créé malgré l'absence de la section
## Métriques de succès— refus manquant, violation de la règle anti-lissage du pm-decomposer. - Le pm-decomposer invente des métriques (ex. : « Taux d'adoption : > 50 % ») pour contourner le refus — violation §2.
- Le pm-decomposer considère que les critères d'acceptation tiennent lieu de métriques de succès (confusion entre les deux sections) et crée l'epic.
- Le refus se produit mais avec un message différent qui n'indique pas la cause précise (section absente vs section vague).
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.
- 9d ago First seen · 80 lines · 0 tokens per session scan A 0a9a16585ff2
pm-epic-03-trap-no-metrics is a command published in the GitHub repository evb87-tech/corpus (1 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 718 tokens. 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 commands, from other repositories
status
Show memex statistics and status including projects, memos, and pending items.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.
open
Open the memex vault in Finder or Obsidian.
factory
Run one pass of the ticket queue — scan the tracker for human-authorized tickets, claim one, and route it to the right workflow (spec a raw ticket, groom the backlog, hunt a bug, or build an approved spec in its own worktree via /sonu:build). You are the trigger; there is no daemon. Never merges and never authorizes…
validate
Mechanically validate the sonu plugin repo before a PR — manifest sync, YAML frontmatter, shell-fence syntax, named-source and AI-attribution scans, cross-reference integrity, skill reachability. Only meaningful inside the claude-plugins repo; in any other repo, say so and stop.
test-data-factory
Generate realistic test data, fixtures, and mock factories for testing.