pm-epic-02-edge-vague-metrics

pm-epic-02-edge-vague-metrics is a command for Claude Code from evb87-tech/corpus. It costs 0 tokens per session (706 once invoked), scanned A, original, MIT.

A test case for a product-management command that reads a PRD, or product requirements document, with vague success measures. It checks that the command keeps those measures unchanged while warning that they may fail validation.

In plain words
What is it for?
Use it when testing PRD-to-epic conversion, especially how vague success metrics and acceptance criteria are handled.
Why use it?
It tests an important edge case: unclear goals should be reported rather than silently rewritten.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the corpus-pm plugin — 5 skills, 17 commands, 3 agents shipped together

Good fit Use it when testing PRD-to-epic conversion, especially how vague success metrics and acceptance criteria are handled.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/evb87-tech/corpus/pm-epic-02-edge-vague-metrics
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.

Clone the repo
git clone --depth 1 https://github.com/evb87-tech/corpus

Made for: Claude Code.

Or install corpus-pm, the plugin that ships this one along with the rest of its 5 skills, 17 commands, 3 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-epic-02-edge-vague-metrics

README.md
[![agentmods](https://agentmods.dev/badge/commands/evb87-tech/corpus/pm-epic-02-edge-vague-metrics/github.svg)](https://agentmods.dev/commands/evb87-tech/corpus/pm-epic-02-edge-vague-metrics)
Your own site
<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.

agentmods 80×15 button for pm-epic-02-edge-vague-metrics

Your own site · 80×15
<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>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 706 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00706
Opus 5 $0.00000 $0.00353
Sonnet 5 $0.00000 $0.00141
Haiku 4.5 $0.00000 $0.00071

Measured 10d ago against content hash 7141e66d13e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

corpus-pm/evals/commands/pm-epic-02-edge-vague-metrics.md · 74 lines

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 succès existe).
  • La section ## Success Criteria de l'epic contient les métriques telles quelles (verbatim), sans réécriture ni amélioration.
  • Le récapitulatif final ou le résultat de bd lint signale que les métriques sont vagues ou potentiellement non conformes aux critères de bd 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.

Read the full file on GitHub · 74 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. 10d ago First seen · 74 lines · 0 tokens per session scan A 7141e66d13e3

Subscribe to this mod's changes

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.