Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/SoliEstre/EstreGenesisnpx agentmods add skills/soliestre/estregenesis/compendium-lintWrote 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/soliestre/estregenesis/compendium-lint)<a href="https://agentmods.dev/skills/soliestre/estregenesis/compendium-lint"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/compendium-lint/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/soliestre/estregenesis/compendium-lint"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/compendium-lint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00146 | $0.00842 |
| Opus 5.5 | $0.00058 | $0.00337 |
| Sonnet 5.5 | $0.00029 | $0.00168 |
| Haiku 4.5 | $0.00015 | $0.00084 |
Grade A, and why
compendium-lint 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compendium Lint — gardening checks for the vocabulary store
A controlled-vocabulary store degrades silently: a renamed heading orphans a pointer, a copied definition drifts, a superseded term keeps getting cited. These checks make that degradation computable, like a build's verify pass. Four hard (build-failing) + three soft (gardening signal) — seven checks total. This is the runtime's severity view of the spec's §9 grouping: the four gardening lints (broken-link · orphan · duplicate-concept · stale) plus the pointer-resolution check (slug resolution · no-competing-full-def · redaction) — same seven, sliced by severity instead of by family.
If the runtime is present (preferred)
node plugins/compendium/lint.cjs # check only
node plugins/compendium/lint.cjs --reindex # check + regenerate INDEX.md / index.json + the viewer-agnostic [[id]] projection
node plugins/compendium/lint.cjs --quiet # exit code only (CI)
Exit 1 on any hard failure; 0 otherwise. Hard failures must be fixed before commit; soft warnings are a gardening worklist.
If no runtime — apply the checks by inspection
HARD (must fix):
- broken-link — every id in
links:resolves to an existing entry id. A dangling peer link is a hard failure. - pointer-resolution —
owner_specis of the form<file>#<slug>, the file exists, and the slug is an actual heading in that file (GitHub-style slug: lowercase, spaces→-, punctuation dropped). A pointer to a heading that no longer exists is the most common rot. - no-competing-full-def — an
internal-register entry'sdefinition.textstays under the one-line cap; a long restatement = a competing SSoT (the pointer-not-paraphrase violation). - redaction — a conversation-sourced term carries no leaked private/governance content (only settled technical vocabulary reaches a published store).
SOFT (gardening worklist):
5. orphan — an entry with zero inbound links that is not an index: confirm it is genuinely cross-cutting, or wire it in.
6. duplicate-concept — two active entries sharing a concept/title-slug that contradict: merge, or supersede one (status: superseded + superseded_by).
7. stale — audit.updated lags behind a superseding note elsewhere.
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 · 38 lines · 146 tokens per session scan A 16f4f03c8433
compendium-lint is a skill published in the GitHub repository SoliEstre/EstreGenesis (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 146 tokens to every session and 842 once invoked, about $0.0006 per session on Opus 5.5. 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
submit-github-pr
Use when publishing an existing TensorRT-Model-Connect change as a GitHub pull request. Verifies authenticated repository access, branch and diff scope, validation evidence, commit identity, reviewer-facing text, exact pushed head, and the created draft PR without merging it.
answer-audit
Adversarially audit a RAG answer against the corpus it claims to cite. Use when asked to review, critique, sanity-check, or "give skeptical feedback on" an answer produced by Canon (or any retrieval-grounded system) — especially when the answer looks good. Assumes the answer is wrong until each claim is proven…
x-bug2rag
A knowledge-capture tool that turns reusable bug explanations into a local RAG collection, meaning a searchable store of text that an agent can retrieve later. It records the trigger, incorrect implementation, correct implementation, and observable difference.
x-dev-rag-call
A local semantic search tool that finds relevant passages in specified Markdown or text files. It uses an embedding model, which represents meaning as numbers, to return the closest passages for a question or plan.
pocket-development
Execute Pocket implementation plans through bounded packets, delegated implementation, independent review, and phase handoff. Use when the user asks to execute a plan or dispatch its tasks.
pocket-pitching
Pre-grinding problem exploration. Use BEFORE pocket-grinding when the problem is unformed or needs exploration. Guides diverge→converge with structured brainstorming methods and independent advisor curation (advisor tool or advisor subagent fallback), then produces a pitch exploration doc. Trigger on…