kit-check-blast
Skill6 starsChanged 27 days agoMITView on GitHub
Find what a change could break beyond the diff, and prove the one fact that makes it safe by running real code. Use before shipping a small diff you don’t fully trust.
In this repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- rules/AGENTS.mdAGENTS.md
- kit-audit-metricsSkill
- kit-audit-skillsSkill
- kit-capture-lessonSkill
- kit-challenge-designSkill
- kit-create-prSkill
- kit-debate-decision-treeSkill
- kit-debug-prodSkill
- kit-decisionsSkill
- kit-evolveSkill
- kit-explainSkill
- kit-learn-repoSkill
- kit-minimizeSkill
- kit-optimize-contextSkill
- kit-planSkill
- kit-proveSkill
- kit-reviewSkill
- kit-strip-diffSkill
- kit-triage-commentsSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Not a full PR review (kit-review)
- Very specific: line 14
Not cutting unused additions or format-only hunks (kit-strip-diff)
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Check Blast
What else breaks if this ships? Grep alone is not enough.
What this is NOT
- Not a full PR review (
kit-review) - Not cutting unused additions or format-only hunks (
kit-strip-diff) - Not “list every caller” — that’s trivial; focus on breakage grep misses
- Companion to
kit-prove: safety claims need live proof
Flow
- Read the change — symbols added/changed/deleted; behavior the diff doesn’t spell out.
- Find the one safety fact — the single assumption that clears most risk if true (e.g. “this only drops already-dead cache entries”).
- Look where grep stops — library source + pinned version, timing/teardown, wire formats, flags, other languages/services reading the same bytes.
- Rank risks — real chance × real cost. Keep confirmed risks; list cleared checks separately. Cite
file:line; never invent callers. - Prove the safety fact — small script/test that calls the real code and fails loud if wrong. Paste output. If you can’t reach a run cheaply, mark unproven.
Hand back
- Safety fact + proof artifact (or unproven)
- Confirmed risks (chance/cost + citation)
- Cleared checks
- Recommended next step (ship / narrow / add test / ask human)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

