# Definition Of Done

> The ordered finish-line runner for any change in this repo — generators, then the asset-integrity refresh last on its own, then the full gate suite, then commit and push; use before declaring any change finished or whenever the stop hook reports uncommitted or untracked changes.

- **Type:** Skill
- **Install:** `agentstack add skill-vincentchuwaichow-vanguard-frontier-agentic-definition-of-done`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [VincentChuWaiChow](https://agentstack.voostack.com/s/vincentchuwaichow)
- **Installs:** 0
- **Category:** [Cloud & Infrastructure](https://agentstack.voostack.com/c/cloud-infrastructure)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [VincentChuWaiChow](https://github.com/VincentChuWaiChow)
- **Source:** https://github.com/VincentChuWaiChow/vanguard-frontier-agentic/tree/master/.claude/skills/definition-of-done

## Install

```sh
agentstack add skill-vincentchuwaichow-vanguard-frontier-agentic-definition-of-done
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Definition of Done

## Doctrine

The order is load-bearing. The integrity manifest must hash the settled tree, so
`asset-integrity:write` always runs last, on its own, from the repo root — never folded into a
parallel generator batch, never run from a subdirectory.

## Trigger

- Before declaring any change in this repo finished.
- Whenever the stop hook reports uncommitted or untracked changes.

## Input

The list of paths you touched in this change.

## Decision matrix

Pick the steps that apply based on what changed — most changes trigger more than one row.

- **catalog / agents / skills / roles / providers changed** → `npm run manifest:write:all`,
  then re-run asset-integrity LAST on its own (the parallel-generator ordering caveat in
  `CLAUDE.md`).
- **`skills/**` changed** → `npm run manifest:write`.
- **`catalog/model-policy.json` or `model-registry.json` changed** → `npm run
  model-policy:check` (and `model-policy:apply` if the projection changed).
- **`tools/vfa-tui/**` changed** → `cd tools/vfa-tui && cargo fmt --check && cargo clippy
  --all-targets -- -D warnings && cargo test`. Return to the repo root afterwards — a
  persisted `cd` has broken integrity runs before.
- **any root file / `agents/` / `plugins/` / `package.json` changed** → asset-integrity
  refresh required.

## The invariant sequence

Always, in this order:

1. Applicable generators from the decision matrix above.
2. `python3 tests/validate-asset-integrity.py --write` from the REPO ROOT, last, on its own.
3. `npm run validate` — zero failures.
4. `npm run lint:spell` and `npx --yes markdownlint-cli2 "**/*.md" "#node_modules"` — zero
   failures.
5. `git status` clean after committing with a scoped conventional-commit message.
6. `git push -u origin ` (retry with backoff on network errors only).

## Footguns

- `grep -cE 'FAIL|ERROR'` exits 1 on a count of 0 — do not chain it with `&&` before the
  commit, or a clean gate run looks like a failure and blocks you.
- Run integrity from the repo root — a leftover `cd` into `tools/vfa-tui` makes the write
  silently target a nonexistent path.
- Warnings from model-policy are exit-0 by design — read them, don't treat them as failures.
- Never edit `catalog/asset-integrity.json` by hand.

## Output

The checklist above with pass evidence per step, then the commit hash and push confirmation.

## Delegation note

Gate runs may be delegated to a Haiku subagent per `agentic-delegation`'s "Gate run" workflow
template, but the orchestrator reads the results and owns the commit — a delegate's self-report
that gates passed is not verification.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [VincentChuWaiChow](https://github.com/VincentChuWaiChow)
- **Source:** [VincentChuWaiChow/vanguard-frontier-agentic](https://github.com/VincentChuWaiChow/vanguard-frontier-agentic)
- **License:** Apache-2.0

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-vincentchuwaichow-vanguard-frontier-agentic-definition-of-done
- Seller: https://agentstack.voostack.com/s/vincentchuwaichow
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.