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-02-edge-vague-metrics)<a href="https://agentmods.dev/commands/evb87-tech/corpus/pm-epic-02-edge-vague-metrics"><img src="https://agentmods.dev/badge/commands/evb87-tech/corpus/pm-epic-02-edge-vague-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-02-edge-vague-metrics"><img src="https://agentmods.dev/badge/commands/evb87-tech/corpus/pm-epic-02-edge-vague-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 | $0.00706 |
| Opus 5 | $0.00000 | $0.00353 |
| Sonnet 5 | $0.00000 | $0.00141 |
| Haiku 4.5 | $0.00000 | $0.00071 |
Grade A, and why
pm-epic-02-edge-vague-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 10d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scénario
Un PRD est disponible dans output/. Il contient une section ## Métriques de succès
(donc le pm-decomposer ne refuse pas) mais les métriques sont vagues et non mesurables
(ex. : « améliorer la satisfaction utilisateur »). Les exigences P0 ont des critères
d'acceptation. Le comportement attendu est que l'epic est créé avec les métriques
telles quelles, mais que le récapitulatif final signale que les métriques sont vagues
et pourraient ne pas passer bd lint. Le pm-decomposer ne les réécrit pas.
Setup
Créer le PRD de test dans output/ :
output/2026-04-28-feature-commentaires-prd.md (voir evals/fixtures/pm-epic-prd-edge.md)
Structure attendue du PRD (extraits pertinents) :
# Commentaires collaboratifs sur les décisions
## Exigences
### P0 — Ajout de commentaires
Un utilisateur peut ajouter un commentaire textuel à une décision.
### P1 — Mentions
Un utilisateur peut @mentionner un collègue dans un commentaire.
## Critères d'acceptation
- P0 Commentaires : le commentaire s'affiche sous la décision en < 500 ms.
- P1 Mentions : la @mention envoie une notification email dans < 1 min.
## Métriques de succès
- Améliorer la satisfaction utilisateur sur la collaboration.
- Augmenter l'engagement avec les décisions passées.
Prompt
/pm-epic output/2026-04-28-feature-commentaires-prd.md
Pass criteria (rubric)
- L'epic est créé (le pm-decomposer ne refuse pas car la section
## Métriques de succèsexiste). - La section
## Success Criteriade l'epic contient les métriques telles quelles (verbatim), sans réécriture ni amélioration. - Le récapitulatif final ou le résultat de
bd lintsignale que les métriques sont vagues ou potentiellement non conformes aux critères debd lint. - Les issues enfants P0 et P1 sont créées avec leurs critères respectifs.
- Aucune métrique n'est inventée ou précisée par le pm-decomposer pour compléter les métriques vagues — violation §2.
- Les enfants sont liés à l'epic.
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.
- 10d ago First seen · 74 lines · 0 tokens per session scan A 7141e66d13e3
pm-epic-02-edge-vague-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 706 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
save
Manually save current context as a memo to the memex vault.
status
Show memex statistics and status including projects, memos, and pending items.
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…
ship
Prepare the current branch to ship, commit messages, semver bump, and a PR description, all for approval.
pm-agent-retire
Mark a great-pm agent as deprecated. Adds a deprecation banner to the agent file, files a Beads issue to remove dependent commands/workflows, and logs the rationale. NEVER deletes the file (history preserved).