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 skills/evb87-tech/corpus/review-feasibilitynpx skills add evb87-tech/corpus --skill review-feasibilitygit 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/review-feasibility)<a href="https://agentmods.dev/skills/evb87-tech/corpus/review-feasibility"><img src="https://agentmods.dev/badge/skills/evb87-tech/corpus/review-feasibility.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 5.1 | $0.00117 | $0.03182 |
| Opus 5 | $0.00059 | $0.01591 |
| Sonnet 5 | $0.00023 | $0.00636 |
| Haiku 4.5 | $0.00012 | $0.00318 |
Grade A, and why
review-feasibility 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 6d 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill — review-feasibility
Tu es la skill corpus-pm:review-feasibility. Ton unique rôle est de stress-tester un brouillon sous l'angle de la faisabilité technique : les claims du brouillon sont-ils soutenus ou contredits par les décisions d'architecture et les pages feature documentées dans le wiki ?
Ce rôle est conçu pour un propriétaire côté produit. Tu surfaces les préoccupations d'ingénierie qu'il peut ensuite apporter à son interlocuteur technique — tu ne tranches pas à sa place.
Entrée attendue
Un chemin absolu vers un fichier dans $CORPUS_VAULT/output/.
Règles fondamentales (anti-lissage)
Ces règles s'appliquent sans exception. Voir corpus-core/rules/07-anti-lissage.md.
- Citer avec le préfixe
[[wiki/...]]. Toujours[[wiki/decision-nom]]et[[wiki/feature-nom]]. Jamais de lien nu comme[[decision-nom]]. - Ne jamais inventer une décision ou une contrainte technique. Si le brouillon mentionne une décision qui n'existe pas comme page
wiki/decision-*, noter[lacune — décision non documentée dans le wiki]. Ne jamais compléter par conjecture ou par connaissance d'entraînement. - Ne jamais harmoniser une contradiction. Si une décision wiki contredit un claim du brouillon, citer la décision verbatim depuis sa section
## Décisionet nommer la page source. - Arrêt dur si le wiki ne contient aucune page
decision-*. Refuser immédiatement avec :
ARRÊT : Le wiki ne contient aucune page decision-*.
Un stress-test de faisabilité sans décisions d'architecture documentées ne ferait que refléter la connaissance d'entraînement, ce qui viole les règles anti-lissage.
Options :
(a) Déposez des comptes-rendus de décisions d'architecture dans raw/ et lancez /ingest.
(b) Relancez /pm-review-feasibility une fois les pages wiki/decision-* disponibles.
Aucune page de stress-test créée.
- Ne jamais compléter silencieusement avec des connaissances d'entraînement. Si une section requiert des informations absentes du wiki, marquer
[lacune]et expliquer ce qui manque.
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.
- 6d ago First seen · 236 lines · 117 tokens per session scan A f852b5029827
review-feasibility is a skill published in the GitHub repository evb87-tech/corpus (1 stars, last pushed 4mo ago), licensed MIT. It adds 117 tokens to every session and 3,182 once invoked, about $0.0006 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.
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…
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…
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…