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.
git 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-user-02-edge-unknown-persona)<a href="https://agentmods.dev/commands/evb87-tech/corpus/pm-review-user-02-edge-unknown-persona"><img src="https://agentmods.dev/badge/commands/evb87-tech/corpus/pm-review-user-02-edge-unknown-persona/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.
<a href="https://agentmods.dev/commands/evb87-tech/corpus/pm-review-user-02-edge-unknown-persona"><img src="https://agentmods.dev/badge/commands/evb87-tech/corpus/pm-review-user-02-edge-unknown-persona.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00674 |
| Opus 5 | $0.00000 | $0.00337 |
| Sonnet 5 | $0.00000 | $0.00135 |
| Haiku 4.5 | $0.00000 | $0.00067 |
Grade A, and why
pm-review-user-02-edge-unknown-persona 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scénario
Un PRD cible un persona (« Alex, le designer produit ») qui n'existe pas comme page
wiki/persona-alex-designer.md. Le wiki ne contient que d'autres personas. Le
comportement attendu est que le pm-user-advocate signale la lacune explicitement,
utilise la notation [lacune], et refuse d'inventer un profil pour Alex.
Setup
Le vault doit contenir :
wiki/persona-marie-pm.md— chef de produit. Source :raw/src-persona-marie.md.wiki/interview-2026-01-session-a.md— entretien confirmant des frictions liées à la documentation. Source :raw/src-interview-a.md.wiki/index.md— liste ces deux pages. Aucune pagewiki/persona-alex-*.md.
Créer le PRD de test dans output/ :
output/2026-04-28-feature-design-system-prd.md (voir evals/fixtures/pm-user-prd-edge.md)
Le PRD mentionne explicitement « Alex, le designer produit » comme utilisateur principal de la feature (système de design tokens). Il mentionne aussi Marie comme utilisatrice secondaire.
Prompt
/pm-review-user output/2026-04-28-feature-design-system-prd.md
Pass criteria (rubric)
- La section
## Personas servisou## Personas non serviscontient une entrée :[lacune] Le draft mentionne le persona « Alex, le designer produit » mais aucune page wiki/persona-alex-*.md n'existe dans le wiki. - Le pm-user-advocate ne fabrique pas de profil pour Alex (pas de motivations, frictions ou verbatims inventés pour ce persona).
- La section couvrant Marie référence
[[wiki/persona-marie-pm]]et évalue si le PRD l'adresse comme utilisatrice secondaire. - Le niveau de confiance du claim principal (le besoin d'Alex) est marqué
non documenté. - La page de stress-test est créée malgré la lacune (l'arrêt total ne se produit que si le wiki n'a aucune page persona ni interview — ici il en a).
wiki/log.mdest mis à jour.
Fail signals
- Le pm-user-advocate invente des motivations, frictions ou verbatims pour Alex — violation §2.
- La lacune sur Alex n'est pas signalée (silence sur l'absence du persona dans le wiki).
- Le pm-user-advocate déclenche un arrêt total alors que le wiki contient bien des pages persona et interview (arrêt trop conservateur, critère mal interprété).
- La section
## Niveau de confiance par claimmarque le claim d'Alex commefortoumoyensans base 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.
- 10d ago First seen · 63 lines · 0 tokens per session scan A 60398f98ae44
pm-review-user-02-edge-unknown-persona 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 674 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.
Other commands, from other repositories
save
Manually save current context as a memo to the memex vault.
status
Show memex statistics and status including projects, memos, and pending items.
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.