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 commands/evb87-tech/corpus/pm-review-feasibilitygit 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-review-feasibility)<a href="https://agentmods.dev/commands/evb87-tech/corpus/pm-review-feasibility"><img src="https://agentmods.dev/badge/commands/evb87-tech/corpus/pm-review-feasibility.svg" alt="Measured on agentmods" 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 | $0.00069 | $0.00749 |
| Opus 5 | $0.00034 | $0.00375 |
| Sonnet 5 | $0.00014 | $0.00150 |
| Haiku 4.5 | $0.00007 | $0.00075 |
Grade A, and why
pm-review-feasibility scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Pré-vol :
CORPUS_VAULT="${CORPUS_VAULT:-$CLAUDE_PLUGIN_OPTION_VAULT_PATH}"
if [ -z "$CORPUS_VAULT" ]; then
echo "Vault non configuré. Définir CORPUS_VAULT (dev local) ou configurer l'option utilisateur vaultPath dans le plugin installé (exposée sous CLAUDE_PLUGIN_OPTION_VAULT_PATH). Ni l'un ni l'autre n'est défini. Lancez /init-vault <chemin> pour initialiser un vault, puis exportez le chemin." >&2
exit 1
fi
Vérifier que $CORPUS_VAULT/.corpus-vault existe. Sinon, refuser et demander au propriétaire de lancer /init-vault <chemin>. Voir corpus-core/rules/08-vault-structure.md.
Validation de l'argument :
$ARGUMENTS doit être fourni. Si absent, afficher :
Usage : /pm-review-feasibility <chemin-vers-brouillon>
Le chemin peut être absolu ou relatif à $CORPUS_VAULT/output/.
Exemple : /pm-review-feasibility output/2026-04-28-ma-feature-prd.md
et s'arrêter.
Résoudre le chemin du brouillon :
- Si
$ARGUMENTSest un chemin absolu, l'utiliser tel quel. - Sinon, le résoudre sous
$CORPUS_VAULT/output/:$CORPUS_VAULT/output/$ARGUMENTS(supprimer le préfixeoutput/s'il est déjà présent).
Vérifier que le fichier résolu existe et se trouve bien sous $CORPUS_VAULT/output/. Si le fichier n'existe pas ou est en dehors de output/, refuser avec un message explicite.
Délégation :
Invoquer la skill corpus-pm:review-feasibility (voir corpus-pm/skills/review-feasibility/SKILL.md) en lui passant le chemin absolu résolu du brouillon.
La skill s'occupe de :
- Lire le brouillon et identifier les claims techniques.
- Scanner
wiki/decision-*etwiki/feature-*pour chaque claim. - Détecter les conflits entre le brouillon et les décisions d'architecture documentées.
- Produire l'analyse en quatre axes : faisabilité des claims, dépendances, risques d'intégration, décisions contredites.
- Écrire la page de stress-test dans
$CORPUS_VAULT/wiki/stress-test-<draft-slug>-feasibility-<YYYY-MM-DD>.md. - Appendre l'entrée dans
wiki/log.md.
Contrainte anti-lissage : si le wiki ne contient aucune page decision-*, la skill doit refuser avec un arrêt dur et orienter le propriétaire vers /ingest. Elle ne doit jamais inventer des décisions d'architecture ou des contraintes techniques absentes du wiki.
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.
- 5d ago First seen · 50 lines · 69 tokens per session scan A b91e41b1fdbe
pm-review-feasibility is a command published in the GitHub repository evb87-tech/corpus (1 stars, last pushed 4mo ago), licensed MIT. It adds 69 tokens to every session and 749 once invoked, about $0.0003 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 commands, from other repositories
save
Manually save current context as a memo to the memex vault.
open
Open the memex vault in Finder or Obsidian.
sol
Run a one-shot task on the routed Codex model (gpt-5.6-sol by default) and relay its answer.
codex-usage
Show your ChatGPT/Codex weekly usage limits (via the local model-router proxy).
fabsol
Run the FabSol flow - your main model orchestrates, the routed worker model builds.
broadcast
Run broadcast on a distilled Raw — update related existing pages conversationally.