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 commands/evb87-tech/corpus/check-01-happygit 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/check-01-happy)<a href="https://agentmods.dev/commands/evb87-tech/corpus/check-01-happy"><img src="https://agentmods.dev/badge/commands/evb87-tech/corpus/check-01-happy.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 | $0.00000 | $0.00557 |
| Opus 5 | $0.00000 | $0.00279 |
| Sonnet 5 | $0.00000 | $0.00111 |
| Haiku 4.5 | $0.00000 | $0.00056 |
Grade A, and why
check-01-happy 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.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scénario
Le wiki est dans un état sain : toutes les pages ont un frontmatter valide, les liens
[[wikilinks]] pointent vers des pages existantes, index.md est à jour et aucune
page n'est orpheline. La commande /check doit produire un rapport propre et mettre à
jour wiki/log.md. Elle ne doit rien modifier dans le wiki au-delà du log.
Setup
Le vault doit contenir un wiki minimal mais cohérent :
wiki/index.md— liste toutes les pages présentes.wiki/discovery-produit.md— frontmatter valide (type,sources,last_updated), un lien sortant[[wiki/interview-utilisateur]], pas de lien mort.wiki/interview-utilisateur.md— frontmatter valide, lien entrant depuiswiki/discovery-produit.md.wiki/log.md— au moins une entrée historique.- Les deux fichiers
raw/correspondants auxsources:existent.
Prompt
/check
Pass criteria (rubric)
- Le librarian inspecte toutes les pages de
wiki/. - Le rapport final liste :
- Liens brisés : 0
- Pages orphelines : 0
- Pages ultra-connectées (> 20 liens entrants) : 0
- Pages stales : 0 (ou liste explicite si certaines dépassent 6 mois)
wiki/index.md: synchronisé- Violations frontmatter : 0
- Une ligne de résumé est ajoutée dans
wiki/log.md. - Aucune page wiki n'est modifiée (le check est read-only sauf pour
log.md). - Le rapport identifie 3 à 5 questions ouvertes (concepts sans page dédiée ou lacunes de contenu) — même dans un wiki sain, quelques investigations sont proposées.
Fail signals
- Le librarian modifie une page wiki pour corriger une erreur (il doit signaler, pas
corriger) — seul
wiki/log.mdpeut être modifié. - Le rapport ne mentionne pas les pages consultées.
wiki/log.mdn'est pas mis à jour.- Le rapport ne contient pas de section sur les questions ouvertes ou les investigations suggérées (lint scope Karpathy).
- Le librarian ne signale pas une page
last_updatedà plus de 6 mois même si elle existe dans ce vault de test.
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.
- 4d ago First seen · 59 lines · 0 tokens per session scan A 6add29c867ff
check-01-happy 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 557 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
discover
Generate a substantive project note for the current (or specified) repo. Forces a fresh discovery — if a project note already exists, appends a new ## SuperBrain discovery (date) section without clobbering existing content. Use when SuperBrain didn't auto-discover (e.g., the project's slug collided with a note…
inject
Inject freeform text into the SuperBrain vault. SuperBrain splits multi-topic input, places each item in the right scope (project / decision / capture / etc.), links related notes, and updates today's daily note. Short single-blob input is preserved verbatim; longer or multi-paragraph input is split via the inject…
adopt
Adopt an existing directory as the SuperBrain vault (marks it, indexes existing notes).
migrate
Import an existing Obsidian vault into SuperBrain's structure — non-destructive (source is read-only; SuperBrain's vault gets copies). Optional path argument; otherwise Claude finds the vault.
save
Manually save current context as a memo to the memex vault.
status
Show memex statistics and status including projects, memos, and pending items.