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/execute-criterion/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/execute-criterion)<a href="https://agentmods.dev/skills/fulminate-io/knowledge-mcp/execute-criterion"><img src="https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/execute-criterion/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/execute-criterion"><img src="https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/execute-criterion.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 | $0.00051 | $0.00906 |
| Opus 5.5 | $0.00020 | $0.00362 |
| Sonnet 5.5 | $0.00010 | $0.00181 |
| Haiku 4.5 | $0.00005 | $0.00091 |
Grade A, and why
execute-criterion 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EXECUTE-CRITERION — running a stored gate and recording what it said
Run the stored bytes
A brief or plan naming a gate in prose is a POINTER you resolve in the graph. Fetch the criterion node and run the command from THAT response, written to a file (inline retyping mangles quoting classes — a measured false red). A file in /tmp whose name matches the gate is another lane's materialization, possibly of a superseded revision. Establish an instrument's provenance in one call before theorizing about its result; after transcribing any gate, prove your copy can fail (one documented red) before trusting its green. Plans are revised while you work: fetch at the START of each unit, never from an earlier read.
Classify with evidence
Every execution is classified with observed exit status and first output line PASTED: FAILS-AS-EXPECTED · PASSES-ALREADY (legitimate only for labeled characterization guards and scope fences; otherwise vacuous — a finding) · FAILS-MALFORMED (a finding) · NOT-RUN (concrete reason; a destructive command is not run — that is itself a finding). A label without pasted evidence, or contradicted by your run, is a finding about the rigor story.
Vacuous-pass shapes (run, don't inspect — each looked right and wasn't)
always-exit-0 pipelines (&& echo BAD || echo OK) · wrong-module go test ./... under a go.work (cd into the module in the command) · -run matching
nothing (anchor the runner's --- PASS: Name line — trailing space, never
$-anchored; $-anchor the selector) · missing build tag (a linter/compiler
not told a tag never checks those files) · empty capture coerced to 0 (test "" -eq 0 passes in zsh; guard with test -n) · a condition already true
pre-implementation · a gate whose script or target the project never defined ·
unquoted glob making n=1 on an empty dir · zsh not word-splitting unquoted
expansions (garbage exit 1 mimics your expected red) · a FAILS-AS-EXPECTED probe
on a conjunction proving only the first failing leg (satisfy the cheap legs so
every expensive leg executes once).
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 · 75 lines · 51 tokens per session scan A b9c35e336a33
execute-criterion is a skill published in the GitHub repository fulminate-io/knowledge-mcp (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 51 tokens to every session and 906 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.