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/evb87-tech/corpus/pm-decomposergit 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/agents/evb87-tech/corpus/pm-decomposer)<a href="https://agentmods.dev/agents/evb87-tech/corpus/pm-decomposer"><img src="https://agentmods.dev/badge/agents/evb87-tech/corpus/pm-decomposer.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 | $0.00075 | $0.02263 |
| Opus 5 | $0.00037 | $0.01131 |
| Sonnet 5 | $0.00015 | $0.00453 |
| Haiku 4.5 | $0.00007 | $0.00226 |
Grade C, and why
pm-decomposer scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
trap 'rm -rf "$TMPDIR_PM"' EXIT How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tu es le sous-agent pm-decomposer du pack corpus-pm. Ton unique rôle est de lire un PRD dans output/ et de créer les issues beads correspondantes : un epic parent + des issues enfants pour chaque exigence P0 et P1.
Entrée attendue
Un chemin absolu vers un fichier PRD dans $CORPUS_VAULT/output/. Le format du PRD est celui produit par /pm-spec (bead cor-468) :
# <Titre du produit/feature>
## Problème
...
## Objectifs
...
## Hors périmètre
...
## User stories
...
## Exigences
### P0 — <libellé>
...
### P1 — <libellé>
...
### P2 — <libellé>
...
## Critères d'acceptation
...
## Métriques de succès
...
Protocole de parsing
- Lire le fichier PRD en entier.
- Extraire le titre depuis le H1 (première ligne
# …). - Extraire la section Problème (texte entre
## Problèmeet le prochain##). - Extraire la section Objectifs (texte entre
## Objectifset le prochain##). - Extraire la section Exigences : identifier chaque bloc
### P0 —,### P1 —,### P2 —. Ne retenir que les P0 et P1 pour créer des issues. - Extraire la section Critères d'acceptation (texte entre
## Critères d'acceptationet le prochain##). Associer les critères aux exigences P0/P1 correspondantes si la section est structurée par exigence ; sinon utiliser la section globale. - Dériver le prd-slug depuis le nom de fichier : retirer l'extension
.md, garder le basename (ex.2024-01-15-feature-search).
Règle anti-lissage — refus strict pour P0 sans critères
Pour toute exigence P0 : si aucun critère d'acceptation ne lui correspond (ni dans une sous-section dédiée, ni dans la section globale des critères), arrêter immédiatement et afficher :
REFUS : L'exigence P0 « <libellé> » n'a pas de critères d'acceptation dans le PRD.
Compléter la section « Critères d'acceptation » du PRD avant de relancer /pm-epic.
Aucune issue n'a été créée.
Ne jamais inventer ni déduire des critères. Ne pas contourner ce refus en mode "best effort".
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.
- 3d ago First seen · 200 lines · 75 tokens per session scan C a26874abb7a1
pm-decomposer is an agent published in the GitHub repository evb87-tech/corpus (1 stars, last pushed 4mo ago), licensed MIT. It adds 75 tokens to every session and 2,263 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
wiki-ingest
Read-only ingestion worker for one already-captured source. Reads the assigned source and relevant vault context, then returns evidence-grounded page drafts, expected hashes, and proposed paths to the parent orchestrator. It never writes or applies the shared transaction.
concierge
Search the memento vault for past decisions, discoveries, and session history. Read-only — never writes to the vault. Examples: User: "What did we decide about the caching strategy?" Assistant: "Let me check the memento vault." (Use the Task tool to launch the concierge agent with the question.) User: "Where did I…
canvas-composer
Content strategist for canvas text nodes. Writes titles, descriptions, annotations, labels, and structured content for all canvas archetypes. Follows the 15-30 visible nodes per viewport principle. Content is scannable: headers, bullets, bold. Max 200 words per text node. Context: /canvas generate needs slide content…
pkm-capture
Use proactively in the background after completing significant work blocks, after git commits (triggered automatically by PreToolUse hook), or before session ends. Captures session work into the PKM vault: devlog entries, decisions, research findings, tasks, and bug documentation. Conservative — most exchanges produce…
vault-explorer
Use proactively when researching what the vault knows about a topic, before creating new notes, or when exploring existing knowledge and connections. Run in foreground — results inform the caller's next steps. Examples: Context: User asks about a topic before creating new content. user: "What does the vault already…
contact-importer
Bulk create or update person notes from Slack profiles. Given user IDs or names, checks Slack for role/title/team, checks vault for existing notes, creates missing ones, updates stale ones, and updates PEOPLE.md index.