pm-decomposer

pm-decomposer is an agent for coding agents from evb87-tech/corpus. It costs 75 tokens per session (2,263 once invoked), scanned C, original, MIT.

An agent that reads a product requirements document and creates a Beads epic with linked child tasks for its P0 and P1 requirements.

In plain words
What is it for?
Use it to create an epic, actionable child issues, acceptance criteria, and parent-child links from a PRD stored in the output folder.
Why use it?
It turns a structured specification into connected implementation work and stops when required P0 acceptance criteria are missing.

Agent

Part of the corpus-pm plugin — 5 skills, 17 commands, 5 agents shipped together

Install

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.

agentmods
npx agentmods add agents/evb87-tech/corpus/pm-decomposer
Clone the repo
git clone --depth 1 https://github.com/evb87-tech/corpus

Or install corpus-pm, the plugin that ships this one along with the rest of its 5 skills, 17 commands, 5 agents.

Wrote 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.

agentmods badge for pm-decomposer

README.md
[![agentmods](https://agentmods.dev/badge/agents/evb87-tech/corpus/pm-decomposer.svg)](https://agentmods.dev/agents/evb87-tech/corpus/pm-decomposer)
Your own site
<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>
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,263 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 3d ago against content hash a26874abb7a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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
corpus-pm/agents/pm-decomposer.md · 200 lines

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

  1. Lire le fichier PRD en entier.
  2. Extraire le titre depuis le H1 (première ligne # …).
  3. Extraire la section Problème (texte entre ## Problème et le prochain ##).
  4. Extraire la section Objectifs (texte entre ## Objectifs et le prochain ##).
  5. Extraire la section Exigences : identifier chaque bloc ### P0 —, ### P1 —, ### P2 —. Ne retenir que les P0 et P1 pour créer des issues.
  6. Extraire la section Critères d'acceptation (texte entre ## Critères d'acceptation et le prochain ##). Associer les critères aux exigences P0/P1 correspondantes si la section est structurée par exigence ; sinon utiliser la section globale.
  7. 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".

Read the full file on GitHub · 200 lines

Changes

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.

  1. 3d ago First seen · 200 lines · 75 tokens per session scan C a26874abb7a1

Subscribe to this mod's changes

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.

Related

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.

AgriciDaniel/claude-obsidian · 53 tokens

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…

sandsower/memento-vault · 151 tokens

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…

AgriciDaniel/claude-canvas · 125 tokens

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…

AdrianV101/obsidian-pkm-plugin · 476 tokens

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…

AdrianV101/obsidian-pkm-plugin · 252 tokens

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.

superuser-pal/awesome-second-brain · 47 tokens