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/instrument-hazards/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/instrument-hazards)<a href="https://agentmods.dev/skills/fulminate-io/knowledge-mcp/instrument-hazards"><img src="https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/instrument-hazards/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/instrument-hazards"><img src="https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/instrument-hazards.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 | $0.00055 | $0.01108 |
| Opus 5 | $0.00028 | $0.00554 |
| Sonnet 5 | $0.00011 | $0.00222 |
| Haiku 4.5 | $0.00006 | $0.00111 |
Grade A, and why
instrument-hazards 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 6d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
INSTRUMENT-HAZARDS — what the tools do to your measurements
Graph-read blind spots
- THE CODE GRAPH IS A SNAPSHOT — line numbers rot immediately. Use search/file_symbols/traverse as locators; the file:line you write comes from having OPENED the file. Wrong ranges cluster in NAVIGATIONAL citations.
- PLAN TREES CARRY NO METADATA:
plan_treeomitsmetadata.commandand truncates descriptions — it is an INDEX. Fetch criteria viaquery(ids:[...], fields:["metadata.command","description","name"]); a criteria review through a tree dump passes vacuously. - GRAPH NODE BODIES HIDE UNDER PROJECTION: thought/finding nodes body in
content—mode:"examine"renders no body and adescriptionprojection returns "". Read them UNPROJECTED (barequery(id:...)) before asserting anything about their contents. Plan/phase/step/criterion nodes body indescription. - AST ENCLOSING FIELDS ARE GRAPH-HYDRATED: file_path/lines are filesystem-true; enclosing_node_id/signature inherit index staleness. Establish containment structurally (contains_pattern) or by opening the file.
- A PER-METADATA-KEY PROJECTION omits the key entirely when a node lacks it — "empty" and "never asked" are indistinguishable in the output; an arm that ignores the projection returns rows shaped as if you asked for nothing.
- PREMISES NEED THE DEFINING ARTIFACT: a comment in file A about a fact defined in file B verifies nothing — go to the artifact that DEFINES it.
Shell semantics are not inferable (each shipped; caught only by execution)
cmd && echo BAD || echo OKalways exits 0. A piped status belongs to the LAST element.- Under a go.work, root
go test ./...is module-scoped — it can test a gen-only module and exit 0 having tested nothing.cdinto the module. -run '^Name$'matching nothing exits 0 — anchor a grep of the runner's^--- PASS: Nameline (trailing space; never$-anchor the PASS line).- go test result lines end with a duration —
$after a test name never matches; anchor with\(or a trailing space. - zsh coerces an empty capture in an integer comparison (
test "" -eq 0→ 0): guard every capture withtest -n, or push the assertion into a script. - zsh does not word-split unquoted expansions — a
set -- $varloop can run garbage whose exit 1 mimics your expected red. - zsh makes
statusa READ-ONLY alias of$?—status=$?is refused and later reads see the live$?. Syntax-check stored commands under both shells (zsh -n,bash -n). - A linter/compiler not told a build tag never checks those files.
- TRUNCATED PIPES MANUFACTURE ABSENCE: a
grep | head -Ncutting before the disproving lines yields a confident false negative — absence claims require the untruncated run.
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.
- 6d ago First seen · 82 lines · 55 tokens per session scan A 9c4657351ad5
instrument-hazards is a skill published in the GitHub repository fulminate-io/knowledge-mcp (1 stars, last pushed 5d ago), licensed Apache-2.0. It adds 55 tokens to every session and 1,108 once invoked, about $0.0003 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.