Borrowing it
Nothing to install: this file belongs to fulminate-io/knowledge-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fulminate-io/knowledge-mcp/main/.claude/skills/author-a-corpus-check/SKILL.mdgit clone --depth 1 https://github.com/fulminate-io/knowledge-mcpWrote 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/fulminate-io/knowledge-mcp/author-a-corpus-check)<a href="https://agentmods.dev/skills/fulminate-io/knowledge-mcp/author-a-corpus-check"><img src="https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/author-a-corpus-check/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/fulminate-io/knowledge-mcp/author-a-corpus-check"><img src="https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/author-a-corpus-check.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 | $0.00045 | $0.00865 |
| Opus 5 | $0.00023 | $0.00432 |
| Sonnet 5 | $0.00009 | $0.00173 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
author-a-corpus-check 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AUTHOR-A-CORPUS-CHECK — durable structural gates in the checks graph
WHY THIS SYSTEM EXISTS: a grep is too narrow to gate a broad defect class — it matches one spelling while the class relocates one construct over. Corpus checks are the first-class instrument for shape assertions: pattern-matched against parsed syntax, admitted only with a proven fixture pair, durable across plans. Reaching for grep on a shape is the defect this rulebook exists to end.
When a criterion is really a check
When a criterion asserts a SHAPE in source — this call pattern is gone, this
construct never appears inside that one — author it as a corpus check
(graph:"checks") and have the criterion name it, instead of a grep command. A
check cannot enter the graph until it has FIRED on a bad fixture and stayed
SILENT on a good one, so admission IS execution and the evidence label is earned
mechanically. The bad fixture is the defect's own shape; the good one is a
NEAR-MISS carrying the same construct where it is legitimate — an unrelated file
proves nothing. A fixture pair proves only the axes it VARIES: give the good
fixture one case per axis the check claims to discriminate on.
Defect classes owe class checks
When work fixes a defect whose signature is expressible as a code shape (an
ast pattern, optionally with a where-tree or dataflow leg), the CLASS check is
authored alongside the instance fix. A fixed instance without its class check
leaves the next author free to reintroduce the shape. The honest split: a check
enforces shape or declaration PRESENCE deterministically; semantic truth stays a
review duty — a check pretending to adjudicate semantics it cannot see is worse
than none. Criteria that are not statically decidable (a rollout landed, a human
accepted, a latency held) stay commands or manual, labeled honestly.
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 Changed · -1 lines eec7cb806e8f
- 8d ago First seen · 71 lines · 45 tokens per session scan A 4d83ef1569d2
author-a-corpus-check is a skill published in the GitHub repository fulminate-io/knowledge-mcp (1 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 865 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.