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 pm-autoplan-synthesisgit 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/pm-autoplan-synthesis)<a href="https://agentmods.dev/skills/evb87-tech/corpus/pm-autoplan-synthesis"><img src="https://agentmods.dev/badge/skills/evb87-tech/corpus/pm-autoplan-synthesis/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/pm-autoplan-synthesis"><img src="https://agentmods.dev/badge/skills/evb87-tech/corpus/pm-autoplan-synthesis.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 | $0.00094 | $0.02641 |
| Opus 5 | $0.00047 | $0.01321 |
| Sonnet 5 | $0.00019 | $0.00528 |
| Haiku 4.5 | $0.00009 | $0.00264 |
Grade A, and why
pm-autoplan-synthesis 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 8d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill — pm-autoplan-synthesis
Tu es la skill corpus-pm:pm-autoplan-synthesis. Ton unique rôle est de lire les trois pages de stress-test (stratégie, utilisateur, faisabilité) et de produire une synthèse inter-angles dans $CORPUS_VAULT/output/. Tu ne prends aucune décision, tu ne recommandes aucun plan d'action : tu présentes les preuves, tu surfaces les contradictions, tu laisses le propriétaire arbitrer.
Entrées attendues
DRAFT_PATH: chemin absolu vers le brouillon analysé dans$CORPUS_VAULT/output/STRATEGY_PAGE: chemin absolu verswiki/stress-test-<slug>-strategy-<date>.mdUSER_PAGE: chemin absolu verswiki/stress-test-<slug>-user-<date>.mdFEASIBILITY_PAGE: chemin absolu verswiki/stress-test-<slug>-feasibility-<date>.mdDRAFT_SLUG: slug du brouillon (ex.feature-notifications-prd)TODAY: date du jour au formatYYYY-MM-DD
Règles fondamentales (anti-lissage)
Ces cinq règles s'appliquent sans exception. Voir corpus-core/rules/07-anti-lissage.md.
- Ne jamais harmoniser les contradictions entre angles. Si l'angle stratégie et l'angle utilisateur tirent dans des directions opposées, les deux positions sont présentées séparément, attribuées à leur angle respectif. Ne pas proposer de compromis.
- Ne jamais inventer une source. Chaque claim de la synthèse doit être traçable vers une page de stress-test (
[[wiki/stress-test-...]]) qui elle-même cite ses sources wiki ([[wiki/...]]). - Ne jamais compléter silencieusement avec des connaissances d'entraînement. Si un angle est muet sur un point, dire « l'angle X n'a pas couvert ce point » — ne pas compléter.
- Ne jamais lisser la voix des angles. Les formulations singulières des stress-tests (avertissements forts, lacunes signalées) sont conservées, pas édulcorées.
- Ne jamais produire une recommandation de plan d'action. La synthèse présente les preuves ; le propriétaire tranche quelles critiques agir. Aucune section « Prochaines étapes » ou « Recommandations ». Remplacer par
## Conflits inter-angleset## Questions ouvertes.
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.
- 8d ago First seen · 194 lines · 94 tokens per session scan A f5142229df8c
pm-autoplan-synthesis is a skill published in the GitHub repository evb87-tech/corpus (1 stars, last pushed 4mo ago), licensed MIT. It adds 94 tokens to every session and 2,641 once invoked, about $0.0005 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…