pm-review-user

pm-review-user is a command for coding agents from evb87-tech/corpus. It costs 72 tokens per session (719 once invoked), scanned A, original, MIT.

A command that reviews a product requirements document or draft from the user-research perspective, including which user types it serves and how strongly the evidence supports each claim.

In plain words
What is it for?
Use it to examine personas, user quotes, contradictory feedback, and confidence in product claims.
Why use it?
It helps reveal when a draft overlooks users, relies on weak evidence, or conflicts with what users have actually said.

Command

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 commands/evb87-tech/corpus/pm-review-user
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-review-user

README.md
[![agentmods](https://agentmods.dev/badge/commands/evb87-tech/corpus/pm-review-user.svg)](https://agentmods.dev/commands/evb87-tech/corpus/pm-review-user)
Your own site
<a href="https://agentmods.dev/commands/evb87-tech/corpus/pm-review-user"><img src="https://agentmods.dev/badge/commands/evb87-tech/corpus/pm-review-user.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 719 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00072 $0.00719
Opus 5 $0.00036 $0.00360
Sonnet 5 $0.00014 $0.00144
Haiku 4.5 $0.00007 $0.00072

Measured 4d ago against content hash 0a2c45abccdf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pm-review-user 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 4d 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.

corpus-pm/commands/pm-review-user.md · 49 lines

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

Vérifiez que $CORPUS_VAULT/.corpus-vault existe. Si absent, refusez et indiquez 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-user <chemin-vers-draft>
Le chemin peut être absolu ou relatif à $CORPUS_VAULT/output/.
Exemple : /pm-review-user output/2026-04-28-feature-notifications-prd.md

et s'arrêter.

Résoudre le chemin du draft :

  • Si $ARGUMENTS est un chemin absolu, l'utiliser tel quel.
  • Sinon, le résoudre sous $CORPUS_VAULT/output/ : $CORPUS_VAULT/output/$ARGUMENTS (supprimer le préfixe output/ 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 :

Déléguer au sous-agent pm-user-advocate (voir corpus-pm/agents/pm-user-advocate.md) en lui passant le chemin absolu résolu du draft.

Le sous-agent s'occupe de :

  1. Lire le draft et identifier les claims utilisateur.
  2. Scanner wiki/persona-* et wiki/interview-* pour chaque claim.
  3. Produire l'analyse en quatre axes : personas servis, personas non servis, verbatims contradictoires, niveau de confiance.
  4. Écrire la page de stress-test dans $CORPUS_VAULT/wiki/stress-test-<draft-slug>-user-<YYYY-MM-DD>.md.
  5. Appendre l'entrée dans wiki/log.md.

Contrainte anti-lissage : si le wiki ne contient aucune page persona-* ni interview-*, le sous-agent doit refuser avec un arrêt total et pointer vers /ingest. Il ne doit jamais inventer des personas ou des verbatims.

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. 4d ago First seen · 49 lines · 72 tokens per session scan A 0a2c45abccdf

Subscribe to this mod's changes

pm-review-user is a command published in the GitHub repository evb87-tech/corpus (1 stars, last pushed 4mo ago), licensed MIT. It adds 72 tokens to every session and 719 once invoked, about $0.0004 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.