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/brainstormnpx skills add evb87-tech/corpus --skill brainstormgit clone --depth 1 https://github.com/evb87-tech/corpusWhat 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 | $0.00079 | $0.02127 |
| Opus 5 | $0.00039 | $0.01064 |
| Sonnet 5 | $0.00016 | $0.00425 |
| Haiku 4.5 | $0.00008 | $0.00213 |
Grade A, and why
brainstorm 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 yesterday.
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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vous conduisez une séance de pression-test (office hours) pour l'idée produit décrite dans $ARGUMENTS, à destination de $CORPUS_VAULT/output/.
Règles fondamentales (anti-lissage)
Ces cinq règles s'appliquent sans exception. Voir corpus-core/rules/07-anti-lissage.md.
- Ne jamais harmoniser les contradictions. Si deux pages wiki se contredisent sur le positionnement ou les personas, citez les deux, attribuez chacune à sa source, et signalez le conflit dans la section concernée.
- Ne jamais inventer une source. Chaque claim tracé dans le rapport doit correspondre à une page wiki existante dans
$CORPUS_VAULT/wiki/. Si vous ne pouvez pas le tracer, vous ne pouvez pas l'écrire. - Ne jamais compléter silencieusement avec des connaissances d'entraînement. Si le wiki est silencieux sur une dimension, dites-le explicitement. N'injectez pas de savoir général sur le marché, les personas génériques ou les tendances sectorielles.
- Ne jamais lisser la voix du propriétaire. Si des pages
decision-*oupositioning-*contiennent des formulations singulières, citez-les verbatim ou paraphrasez minimalement. La singularité est la valeur. - Ne jamais produire ce rapport comme page wiki. Ce rapport est une synthèse produit ; il va dans
output/, jamais danswiki/. Voircorpus-core/rules/04-output-drafting.md.
Phase 1 — Collecte des entités wiki
- Lisez
$CORPUS_VAULT/wiki/index.mdpour identifier les pages pertinentes. - Collectez dans cet ordre de priorité :
Glob $CORPUS_VAULT/wiki/positioning-*.md— positionnement produitGlob $CORPUS_VAULT/wiki/decision-*.md— engagements et décisions passéesGlob $CORPUS_VAULT/wiki/persona-*.md— personas documentésGlob $CORPUS_VAULT/wiki/segment-*.md— segments de marchéGlob $CORPUS_VAULT/wiki/competitor-*.md— concurrents documentésGlob $CORPUS_VAULT/wiki/feature-*.md— fonctionnalités connexes existantes
- Lisez chaque page trouvée en entier avant d'analyser.
- Si
wiki/index.mdest absent ou vide, signalez-le et lisez directement les fichiers globbés.
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.
- yesterday First seen · 157 lines · 79 tokens per session scan A d66d2eb32ba6
brainstorm is a skill published in the GitHub repository evb87-tech/corpus (1 stars, last pushed 4mo ago), licensed MIT. It adds 79 tokens to every session and 2,127 once invoked, about $0.0004 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
wiki-ingest
Ingest supplied source material into an Obsidian vault with provenance and claim tracking: pasted text, files staged in the selected vault's inbox or .raw archive, or explicitly approved URLs. Use for a single source or bounded batch, not for saving an assistant answer. Triggers: ingest, ingest this file, ingest this…
autoresearch
Run a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a separately reviewed canonical vault merge. Use when the user wants autonomous or deep research that may access the public web. Triggers: /autoresearch, autoresearch, research this topic, deep dive into, investigate, find…
wiki-retrieve
Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…
obsidian-bases
Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, or list views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.
qmd
Search the vault using QMD semantic search. Use PROACTIVELY before reading files. Preference order: (1) MCP tools — mcpqmdquery, mcpqmdget, mcpqmdmultiget, mcpqmdstatus — if they appear in your tool menu, use them first; (2) CLI qmd --index ... as fallback; (3) Grep/Glob only when QMD is not installed. Trigger…
obsidian-cli
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their…