Borrowing it
Nothing to install: this file belongs to searlsco/prove_it. 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/searlsco/prove_it/main/.claude/skills/test-local/SKILL.mdgit clone --depth 1 https://github.com/searlsco/prove_itWrote 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/searlsco/prove_it/test-local)<a href="https://agentmods.dev/skills/searlsco/prove_it/test-local"><img src="https://agentmods.dev/badge/skills/searlsco/prove_it/test-local/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/searlsco/prove_it/test-local"><img src="https://agentmods.dev/badge/skills/searlsco/prove_it/test-local.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 | $0.00033 | $0.00556 |
| Opus 5.5 | $0.00013 | $0.00222 |
| Sonnet 5.5 | $0.00007 | $0.00111 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade D, and why
test-local scanned grade D with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/prove_it/config.json Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$tmpdir" What it actually says
Test prove_it locally
Run prove_it from the repo source (not the Homebrew install) to test hook behavior.
Steps
-
Identify the test target. If the user didn't specify, use
example/basic/. -
Set up the PATH shim so
prove_itresolves to the repo'scli.js:export PATH="$(git rev-parse --show-toplevel)/test/bin:$PATH" which prove_it # should show test/bin/prove_it -
Run the requested test. Common scenarios:
Test a specific hook event:
cd example/basic echo '{"hook_event_name":"Stop","session_id":"test","cwd":"."}' | prove_it hook claude:StopTest SessionStart:
echo '{"hook_event_name":"SessionStart","source":"startup","session_id":"test","cwd":"."}' | prove_it hook claude:SessionStartTest PreToolUse (edit protection):
echo '{"hook_event_name":"PreToolUse","tool_name":"Edit","tool_input":{"file_path":"src/greet.js"},"session_id":"test","cwd":"."}' | prove_it hook claude:PreToolUseTest PreToolUse (commit gate):
echo '{"hook_event_name":"PreToolUse","tool_name":"Bash","tool_input":{"command":"git commit -m test"},"session_id":"test","cwd":"."}' | prove_it hook claude:PreToolUseTest init in a temp directory:
tmpdir=$(mktemp -d) cd "$tmpdir" && git init prove_it init --no-default-checks cat .claude/prove_it/config.json prove_it deinit rm -rf "$tmpdir"Test doctor:
cd example/basic prove_it doctor -
Report the output and whether the behavior matches expectations.
Notes
- The shim at
test/bin/prove_itjust doesexec node ../../cli.js "$@" - All
$(prove_it prefix)/libexec/*commands in configs will also resolve through the shim - This tracks with the current git ref—check out any commit to test that version
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.
- 2mo ago First seen · 66 lines · 33 tokens per session scan D 12fdfe246671
test-local is a skill published in the GitHub repository searlsco/prove_it (200 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 556 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
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.
critique
Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.