prove-it
Skill1 starsChanged 29 days agoApache-2.0View on GitHub
Adversarially check whether a cos change does what it claims: the brains stay read-only, every child process is owned and reaped, every chart number comes from facts, the remote MCP server stays free, agents stay sandboxed. Reproduces each finding with a command. Use for \"is this PR ready\", \"prove this works\", \"did this actually ship\" in this repo. Claude Code only: it runs cargo and the cos binary.
28 other projects use a version of this.
Adopted by
Most recently taken up by
- peaknr35/shark-Tank-prooftheir own version, first seen Nov 15, 2026
- dundas/thinkruntheir own version, first seen Nov 9, 2026
- ryanda9910/prove-ittheir own version, first seen Nov 8, 2026
- SaudSatopay/bullseyetheir own version, first seen Nov 8, 2026
- anotherben/claude-harnesstheir own version, first seen Nov 8, 2026
- SylphxAI/skillstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use root-cause, challenge and 4 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Ingramradical235Skillroot-cause
Structured root cause analysis using WHERE (MECE decomposition) then WHY (causal structure diagrams) pipeline. Includes coin-flip detection, logical-leap detection, and vicious cycle intervention. Use when buffer enters YELLOW/RED, when metrics stall, or when Actions execute but don't produce results.
Also in 3 projects that use this
michalattSkillchallenge
Pressure-test plans, decisions, and directions by picking and answering the most relevant challenge questions for the current conversation
Also in 3 projects that use this
renatorozasSkillgrill
Adversarial code review. Don't let me ship until the changes pass your scrutiny.
Also in 4 projects that use this
AWSSkillretro
Conduct a retrospective on a coding session.
Also in 3 projects that use this
MicrosoftSkillhandoff
Compact the current conversation into a handoff document for another agent to pick up.
Also in 3 projects that use this
GoogleSkilltdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
Also in 3 projects that use this
Other versions28 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 28
- nagi-studio/skills★ 470same name
- AlemTuzlak/skills★ 45same name
- Neko-Catpital-Labs/Invoker★ 21same name
- anotherben/claude-harness★ 7same name
- nadirali1350/vetted★ 5same name
- Xnadir/vetted★ 5same name
- SaudSatopay/bullseye★ 4same name
- peaknr35/shark-Tank-proof★ 3same name
- drewdrewthis/claude-skills★ 2same name
- dundas/thinkrun★ 2same name
18 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ritual-fullSkill
- ritualSkill
- semantic-isaSkill
- prove-it-reviewSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 26 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 30
Run them, paste the summary line of each:
“Common” is measured: kept by at least 6 in 10 of the 26 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
prove-it (cos)
The unit of review is a claim ("this ships X"), not a line. For each claim
ask: is there a path where X does not happen? A finding needs a command
whose output is pasted, or a file:line read this session. A kill needs the
same. Nobody gets to assert.
0. Frame
git fetch origin main
BASE=$(git merge-base origin/main HEAD)
git diff -M --name-status "$BASE"..HEAD
gh pr list --search "$(git rev-parse HEAD)" --state all --json number,state,title,bodyMERGED→ stop: nothing reviewed here can land.- Claims come from the PR body's summary bullets, then commit subjects, then
the diff. Print each with an id. Print every changed hunk that maps to no
claim as
unclaimed. - "Improves reliability" is
NOT A CLAIM; say so instead of hunting it.
1. The gates, and what they cannot see
Run them, paste the summary line of each:
cargo fmt --check
cargo clippy --all-targets -- -D warnings
cargo test
cargo run --quiet --example demo -- "$(mktemp -d)/cos-demo"CI runs the same four on macos-latest. They do not see: a live claude or
codex run, the MCP server over a real client, cos dash in a browser,
launchd. Those become hand-checks (§4), never assumptions.
tests/agents.rs and tests/safety.rs start real processes. Inside the
Claude Code Bash sandbox, orphans are reaped at once and worktrees may be
refused. If one fails there, re-run it outside the sandbox before calling it
a defect.
2. The invariants: attack each one the diff touches
| # | Invariant | Pinned by | Attack |
| I1 | A brain has no file, shell or write tool. BRAIN_TOOLS is ToolSearch; READ_ONLY names single connector tools, never a whole server. | tests/safety.rs | grep the diff for Read, Glob, Grep, Bash, Write, Edit, mcp__… without a tool suffix, --permission-mode other than dontAsk in src/claude.rs |
| I2 | The workspace and context/ reach a brain inlined (src/context.rs), capped at LIMIT; nothing in .chief-of-staff/, context/ or out/ is committed; kit fixtures stay fictional. | tests/safety.rs, tests/kit.rs, .gitignore | git diff --name-only $BASE..HEAD -- .chief-of-staff context out must print nothing |
| I3 | Every child cos starts has one owner, one deadline (≤ proc::CEILING; agents ≤ agents::CEILING), is killed with its group and reaped. No Command::spawn/output outside src/proc.rs except short ps/git probes. | tests/safety.rs, tests/agents.rs | git diff $BASE..HEAD -G 'Command::new|\.spawn\(' -- src — for each new spawn: who waits, what deadline, what kills the group |
| I4 | A signal to a pid or group is preceded by an identity check: is_cos, the recorded pgid_started, or comm for the tunnel pidfile. | tests/agents.rs (lost) | every new libc::kill — what stops it hitting a recycled pid? |
| I5 | The remote MCP server (Mode::Remote) offers only REMOTE_TOOLS, filtered in list_tools and call_tool; HTTP answers only /mcp/<token>. | src/mcp.rs | a new #[tool] added to REMOTE_TOOLS, or a filter removed from one of the two methods |
| I6 | cos dash answers only localhost Host headers and serves no path outside out/reports/<date>.html and its fixed routes. | src/dash.rs | a new route reading a path from the URL |
| I7 | Chart and history numbers come from Facts, never from model output. | src/report.rs, src/history.rs | a number in the report traced back to a Brief field |
| I8 | An agent's shell has no network and cannot leave its worktree: Claude with CLAUDE_SANDBOX (strictAllowlist, no unsandboxed retry) and --permission-prompts none; Codex --sandbox workspace-write. No bypassPermissions, no danger-full-access. | tests/harness.rs | any flag added to agents::harness::command |
| I9 | cos agents clean never removes a worktree holding uncommitted changes or commits past its base without --force. | tests/agents.rs | a new removal path that skips clean |
| I10 | A connector the brain could not read is listed in gaps, never rendered as empty. | .claude/agents/*.md | prompt edits that drop the gaps rule |
| I11 | Schemas and structs move together: a new Brief/Week field is in its schema and in its wire type with #[serde(default)]; a brief holds ≤ 3 actions and ≤ 2 changes. | tests/reports.rs | a field added to one and not the other; a cap removed from schema or hold_to_limits |
| I12 | src/state.rs and the kit's scripts/state.py accept and refuse the same states, and each reads what the other commits. | tests/state.rs | a rule changed in one helper only: add the case to parity_cases and run it |
| I13 | cos writes .chief-of-staff/state.json only through state::commit, only when localTracking.approved, never advances a watermark, never steals write.lock. | tests/plan.rs | git diff $BASE..HEAD -G 'atomic_write|state.json' -- src — every write site |
| I14 | With a profile, a brain gets only the connectors of readsApproved sources; the remote server offers no workspace tool (plan, handoff). | tests/plan.rs, src/mcp.rs | context::tools widened; a workspace tool added to REMOTE_TOOLS |
For a fixes-defect claim, also ask whether the sibling call sites have
the same bug (git grep the pattern at HEAD), and whether the fixed
invariant is asserted where it can be broken again.
For anything with a loop, a retry, a poll or a second agent: what happens on
the second item, the failing one, the concurrent run, the abort? The
reconcile race in agents::reconcile (stale Running read, then a dead
supervisor, overwriting Done) was exactly this shape.
3. Reproduce or drop
| Outcome | Result |
| reproduced with a pasted command | defect |
killed with a pasted command or a file:line read this session | CONSIDERED AND DROPPED, one line |
| neither | hand-check, with its pass criterion |
4. Hand-checks the gates cannot do
Print only those the diff makes relevant, each as exact commands and a pass line. None of them spends money unless it says so.
- Brief, live (paid, about $0.35):
cos brief --no-open. Pass: exit 0,out/audit/<day>.jsonlshows noRead/Glob/Greptool call, the brief's gaps name every connector that failed. - Agent, live (paid, capped): in a throwaway repo,
cos --budget 0.25 agents spawn --model haiku --repo <repo> --prompt "run: echo hi > a.txt; then run: curl -sS https://example.com", thencos agents show <id>. Pass:done,a.txtexists in the worktree only, the curl is refused by the sandbox. - Kill: spawn with a long prompt,
cos agents kill <id>, thenps -g <pgid>prints only the header. - Remote MCP:
cos serve --token $(openssl rand -hex 32); a wrong path is 404,tools/listnames onlylatest_brief, a call tobriefis-32602. - Dash:
cos dash --no-open, open/and/agentsin light and dark.
5. Output
CLAIMS HOLD | CLAIM REFUTED | UNPROVEN — n hand-checks outstanding
VERIFY BY HAND (block two, never last, never elided)
CLAIMS C1 HOLDS / REFUTED / UNVERIFIABLE HERE / NOT A CLAIM, each with its evidence
FINDINGS file:line · what fails · the command that shows it · fix
ATTACKS TRIED invariant ids run, and hits
CONSIDERED AND DROPPED always printed, even emptyPost the result as one PR review when a PR is open, inline at each finding's line; otherwise print it. Never edit, commit or push from this skill. No remark on the size of the change, no time estimate, no numeric confidence.
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.

