Skip to content
Agentmart
Submit a tool

implement-work-order

Implement one governed work order from docs/planner specs.

Skill by TribalScale

IndexedApache-2.0★ 2
Write a review

Chalk Labs

Need help deploying implement-work-order?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/tribalscale-implement-work-order

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Implement one governed work order from docs/planner specs. Use when asked to implement WO-NNN or when Primary spec points at docs/planner/work-orders/.

Use cases: backend

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/implement-work-order

What's inside

Skill name
implement-work-order
Description
Implement one governed work order from docs/planner specs. Use when asked to implement WO-NNN or when Primary spec points at docs/planner/work-orders/.
License
Apache-2.0
Compatibility
opencode
Metadata
owner: ts-harness · audience: coding-backend
Instructions
42 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Implement work order

You are implementing **one** work order in a host-managed git worktree.

## Source of truth

1. Read the primary work-order file under `docs/planner/work-orders/` (e.g. `WO-001-*.md`).
2. Use supporting context only as needed:
   - `docs/refinery/` (FRDs, requirements, feature tree)
   - `docs/foundry/` (components, feature blueprints, ADRs)
   - `docs/planner/context-graph.md` and `docs/planner/execution-phases.md`
   - `docs/prd/approved-prd.md` when present
3. Prefer the work order's In Scope / Out of Scope and E2E acceptance criteria over inventing requirements.

## Practice skills (required)

After reading the specs above, load and follow these skills from `.opencode/skills/` only:

1. **`coding-practices`** — TDD (RED-GREEN-REFACTOR), verification before claiming done, and root-cause debugging.
2. **`bdd-acceptance`** — derive/update Gherkin scenarios from the WO and/or `docs/refinery|foundry|planner` when Given/When/Then (or equivalent AC) is derivable, scoped to this WO’s In Scope.

Do not load other skill packs or planning workflows. Specs under `docs/` are already approved.

## Rules

- This is a **non-interactive host run**: implement immediately. Do not ask for approval, present a design for approval, or wait for a human.
- Implement **only** the assigned work order. Do not start sibling WOs.
- Prefer small, testable changes that satisfy acceptance criteria.
- Keep planning markdown under `docs/` in the change set when you touch related files; do not delete those specs.
- Follow existing project conventions, linters, and tests in the repo.
- Do **not** commit, push, or open a pull request — the host coding backend owns git/gh after you finish.
- Do **not** invent secrets, credentials, or external infrastructure outside the work order.
- Installing deps / fixing runners alone is **not** done — ship production code + tests for this WO.

## Done when

- Acceptance criteria for this WO are met (or clearly blocked with a short note in your summary).
- Unit/integration tests for changed behavior are green (TDD per `coding-practices`).
- BDD scenarios added/updated when derivable from the WO and/or planning docs (per `bdd-acceptance`), or an explicit skip for non-behavioral work.
- Diff stays within the work-order scope.

From TribalScale/ts-harness, Apache-2.0.

More from TribalScale/ts-harness

Signals

Stars
2
Forks
0
Open issues
0
Last commit (this folder)
Oct 17, 2026 (14 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from TribalScale

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get implement-work-order running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying implement-work-order?

CallGet help
Cite this page

implement-work-order skill. Agent Mart. https://agentmart.dev/skills/tribalscale-implement-work-order (last updated 2026-10-24)