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 skills add evb87-tech/corpus --skill feature-specgit 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/skills/evb87-tech/corpus/feature-spec)<a href="https://agentmods.dev/skills/evb87-tech/corpus/feature-spec"><img src="https://agentmods.dev/badge/skills/evb87-tech/corpus/feature-spec/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/skills/evb87-tech/corpus/feature-spec"><img src="https://agentmods.dev/badge/skills/evb87-tech/corpus/feature-spec.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 | $0.01578 |
| Opus 5.5 | $0.00000 | $0.00631 |
| Sonnet 5.5 | $0.00000 | $0.00316 |
| Haiku 4.5 | $0.00000 | $0.00158 |
Grade A, and why
feature-spec 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 1mo 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vous rédigez un PRD pour la fonctionnalité décrite dans $ARGUMENTS, à destination de $CORPUS_VAULT/output/.
Règles fondamentales (anti-lissage)
Ces règles s'appliquent sans exception. Voir corpus-core/rules/07-anti-lissage.md.
- Ne jamais inventer un persona. Si aucune page
persona-*n'existe dans le wiki, ne rédigez pas de section User Stories ou Personas sans l'avoir signalé. Marquez la section[lacune — aucun persona dans le wiki]et proposez au propriétaire de déposer une source dansraw/. - Ne jamais inventer un concurrent. Si aucune page
competitor-*n'existe, marquez la section Positionnement[lacune — aucun concurrent dans le wiki]. - Ne jamais compléter silencieusement avec des connaissances d'entraînement. Si une section requiert des informations absentes du wiki, signalez la lacune explicitement. Vous pouvez proposer un contenu de remplissage marqué
[non vérifié — connaissance d'entraînement, non tracée dans le wiki]uniquement si le propriétaire l'accepte explicitement. - Ne jamais harmoniser les contradictions. Si deux pages wiki se contredisent, citez les deux et placez le conflit dans une note sous la section concernée.
- Citer toutes les pages wiki consultées à la fin du document, sous
## Sources wiki.
Taxonomie des sections du PRD
Le PRD produit les sections suivantes, dans cet ordre, en français. Les titres de section sont fixes (ne pas traduire ni reformuler).
1. Problème
Décrivez le problème utilisateur ou métier que cette fonctionnalité résout. Basez-vous sur :
- les champs
## Frictionset## Motivationsdes pagespersona-* - les champs
## Problèmedes pagesfeature-*connexes
Si aucune page pertinente n'existe : [lacune — problème non documenté dans le wiki].
2. Objectifs
Listez les objectifs mesurables de la fonctionnalité. Reliez chaque objectif à une page wiki source quand c'est possible. Format recommandé : liste à puces.
3. Hors périmètre
Listez explicitement ce que cette fonctionnalité ne couvre PAS. Appuyez-vous sur :
- les décisions passées dans
decision-*(alternatives écartées) - les fonctionnalités connexes dans
feature-*qui couvrent déjà certains aspects
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 146 lines · 0 tokens per session scan A ef9a06e3b949
feature-spec is a skill published in the GitHub repository evb87-tech/corpus (1 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,578 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 skills, from other repositories
superbrain-distill
Internal SuperBrain skill — run by the detached capture child to distill a session-event delta into routed Obsidian notes. Not for direct user invocation.
superbrain-recall
Search the user's SuperBrain second-brain vault. Use whenever the user references past work, prior decisions, "how did we", "did we already", earlier sessions, a project's history, or anything that may already be recorded — before answering from scratch.
garden-tending
Tend the knowledge garden — diagnose vault health, condense project memos into project.md overviews, create/merge cross-project topics, fix broken links, archive superseded notes, extend trails. Trigger on "tend the garden", "condense", "update project overview", "check vault health", "where are we with X?", "what…
curator-practice
Operating philosophy for autonomous memex curator tending — orientation protocol, signal triage, bounded work units, initiative thresholds, logging conventions. Trigger on cron-launched runs with no user prompt, "use your judgment", "tend without instructions", "do a pass on the vault", "I'll be away — do what needs…
memo-writing
How to write effective session memos — format, frontmatter schema, observation extraction, topic-signal append. Trigger on /memex:save, "save this for later", "remember this", "save what we discussed", "document this session", "create a memo", or when the [memex] activity nudge appears in context. Do NOT trigger for…
recall
Retrieve session memory across 4 modes — TEMPORAL (date browsing), KEYWORD (FTS lookup), DEEP (cross-session synthesis), LOAD (specific file). Trigger on "what did I do yesterday/last week", "why did we...", "remind me...", "find the memo about...", "last time we...", "patterns across projects", "load the X topic". Do…