dos-verify-done-claims
Before accepting an agent's 'done / shipped / fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's `dos verify` and `dos commit-audit` — never the agent's own narration.
ai-agentsgitquality-gatetrustverification
Verify done-claims against ground truth, not the agent's word
Overview
When an AI agent says "done", "shipped", or "fixed", that is a claim, not a fact — and a claim the agent checks by re-reading its own work is consistency, not grounding. This skill replaces that self-report with a verdict from a witness the agent did not author: it shells the DOS kernel (dos verify, dos commit-audit) to confirm the claimed effect from git ancestry and the commit's actual diff. DOS is deterministic — no API key, no LLM. The verdict is git-only and offline as used here; the one exception is dos verify in a workspace that wires a CI oracle, which --no-ci suppresses (see Security & Safety Notes).
This skill adapts the DOS reference "witness-claim" pattern (anthony-chaudhary/dos-kernel) into a host-agnostic screenplay.
When to Use This Skill
- Use when an agent reports a task/phase/feature as complete and you want
- Use right after a commit, to confirm the commit's message matches its diff
- Use when folding many sub-agents' results — verify each claimed effect instead
- Do not use it to judge whether code is correct — that is what the test
that "done" confirmed from evidence before building on it.
(catch a fix: that only touched a README, or a "tests pass" that deleted the assertions).
of trusting the return string.
suite is for. This s
Subscribers only
The full skill, its 1 bundled files and every download is included with every paid Complete AI plan.
Details
| Source | anthony-chaudhary/dos-kernel |
|---|---|
| License | MIT |
| Risk label | critical ("critical" means the skill may run commands or touch files — read before use) |
| Files | SKILL.md |
| Added | 2026-06-12 |
Related skills
pre-ship-gate
A ship gate that runs before any production deploy: checks the silent failure modes that make a deploy 'succeed' while prod stays broken, then verifies the live revision instead of trusting deploy output.
