Agent skill · Security

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.

Nick44,086★ · +407/wk · 1 repos on radarProfile →
claude-codecodexcursorMIT
Install
npx skills add sickn33/agentic-awesome-skills --skill dos-verify-done-claims --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 8 KB
Bundled scripts: none
Declared author: anthony-chaudhary
Path: skills/dos-verify-done-claims/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 44,414 · +328 this week
Language: Python
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# 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 that "done" confirmed from evidence before building on it. - Use right after a commit, to confirm the commit's **message matches its diff** (catch a `fix:` that only touched a README, or a "tests pass" that deleted the assertions). - Use when folding many sub

What's inside
Steps it walks through
  1. Overview
  2. When to Use This Skill
  3. How It Works
  4. Step 1: Install the kernel (once)
  5. Step 2: Audit the latest commit's claim vs its diff
  6. Step 3: Verify a named phase actually shipped
  7. Step 4: Fold only confirmed effects
  8. Examples
  9. Example 1: gate an agent's "I fixed the bug" claim
  10. Example 2: confirm a feature phase shipped before closing a ticket
  11. Best Practices
  12. Limitations
  13. Security & Safety Notes
  14. Common Pitfalls
Commands it runs
python3 -m venv .dos-venv
python -m pip install 'dos-kernel==<reviewed-version>'  # provides the `dos` CLI
dos commit-audit --workspace . HEAD --json
dos verify --workspace . PLAN PHASE --json --no-ci
The agent committed and said it's fixed. Check the diff backs the claim.
commit-audit --json returns an array, so read the first element's verdict:
dos commit-audit --workspace . HEAD --json | jq -r '.[0].verdict'
OK                -> the change is of the claimed kind; now run the tests
CLAIM_UNWITNESSED -> the commit doesn't do what it says; reject
dos verify --workspace . AUTH AUTH2 --json --no-ci
More from agentic-awesome-skills
All skills →
About this skill
What does the dos-verify-done-claims skill do?

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.

How do I install it?

Run `npx skills add sickn33/agentic-awesome-skills --skill dos-verify-done-claims --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From sickn33/agentic-awesome-skills, a repository with 44,414 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going