Skip to content
Agentmart
Submit a tool

source-work-order

Source adapter that fetches Work Orders from docs/planner and maps them to NormalizedDeliveryContext for verified-merge.

Skill by TribalScale

IndexedApache-2.0★ 2
Write a review

Chalk Labs

Need help deploying source-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-source-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

Source adapter that fetches Work Orders from docs/planner and maps them to NormalizedDeliveryContext for verified-merge. Use when input is WO-###, CWO-###, or a path under docs/planner, or when delivery.source is work-order. Handles dependency checks and optional WO status mirroring on lifecycle events.

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/source-work-order

What's inside

Skill name
source-work-order
Description
Source adapter that fetches Work Orders from docs/planner and maps them to NormalizedDeliveryContext for verified-merge. Use when input is WO-###, CWO-###, or a path under docs/planner, or when delivery.source is work-order. Handles dependency checks and optional WO status mirroring on lifecycle events.
License
Apache-2.0
Instructions
116 lines in SKILL.md · view on GitHub

Before installing

  • Instructions call the network

Files (2)

  • SKILL.md
  • test-scenarios.md

SKILL.md (first lines)

# Source: Work Order

Repo-native source adapter for `verified-merge`. Reads Work Orders from the Planner output, maps them to NormalizedDeliveryContext, and optionally mirrors status on lifecycle events.

## Adapter Contract

Implements the contract in `skills/workflows/verified-merge/adapter-contract.md`:

- `detect(input)` — matches `WO-###`, `CWO-###`, or paths under `docs/planner/**`
- `fetch(id|ref)` — reads Work Order file, context graph, execution phases, linked FRDs/Blueprints
- `on_event(event, payload)` — optional WO status mirror; reads delivery state written by orchestrator
- `capabilities()` — `{ canTransition: false, canComment: false, canLink: true, canUpdateStatus: true }`

## detect(input)

Return true when input matches:

- Work Order id pattern: `WO-[0-9]{3}` or `CWO-[0-9]{3}`
- File path under `docs/planner/`
- User explicitly requests Work Order delivery

Return false for Jira keys and unrelated inputs.

## fetch(id|ref)

### Required reads

Before mapping, read:

- The Work Order file: `docs/planner/epics/**/WO-*.md` or `docs/validator/corrective-work-orders/CWO-*.md`
- `docs/planner/context-graph.md`
- `docs/planner/execution-phases.md`
- Linked FRD and Blueprint files referenced in the Work Order

If the Work Order file cannot be found, stop and report the missing path.

### Dependency gate

From the Work Order context graph `Depends on` links:

1. Read `docs/verified-merge/delivery.json` for dependency status.
2. If a dependency unit is not `Done`, stop and report blocking ids.
3. Do not proceed to implementation until dependencies are resolved or the user explicitly overrides.

### Mapping rules

Map Work Order sections to NormalizedDeliveryContext:

| Work Order section | Context field |
|---|---|
| Title | `title` |
| Summary | `description` |
| Requirements (verbatim) | `requirements[]` |
| E2E Acceptance Tests | `acceptanceCriteria[]` (Given/When/Then form) |
| In Scope / Out of Scope | `scopeBoundaries` |
| Context Graph Depends on | `dependencies[]` |
| WO id | `source.id` |
| File path | `source.ref` |
| `source.type` | `work-order` |
| Branch from id + title slug | `branchHint` |

Set `externalRefs.jira` only when the Work Order or delivery.json already contains a Jira reference. Do not invent external refs.

## on_event(event, payload)

The orchestrator owns writes to `docs/verified-merge/delivery.json`. This adapter:

1. Reads the current delivery state for the unit.
2. Optionally mirrors status to the Work Order markdown file when `mirror_status_to_work_order: true`.

### Status mirror mapping (when enabled)

| Event | WO Status field |
|---|---|
| `context_accepted` or `in_development` | In Progress |
| `pr_opened` | In Review |
| `post_merge_verified` | Done |

When mirroring is disabled (default), do not modify `docs/planner/**`.

Never edit `docs/prd-to-work-orders/manifest.json`.

## capabilities()

```yaml
canTransition: false
canComment: false
canLink: true
canUpdateStatus: true
```

Repo-native status lives in `delivery.json`. External tracker sync is not this adapter's job.

## When to Use

Invoked by `verified-merge` when:

- Input is a Work Order id or planner path.
- Configured `delivery.source` is `work-order`.
- No other adapter matches input more specifically.

## Common Mistakes

| Mistake | Fix |
|---|---|
| Editing upstream manifest | Only read planner artifacts; delivery state is in delivery.json |
| Ignoring dependencies | Check context graph and delivery.json before fetch completes |
| Inventing requirements | Copy Requirements verbatim from Work Order |
| Mirroring WO status by default | Mirror only when config enables it |

## Additional Resources

- Adapter contract: see `verified-merge` workflow `adapter-contract.md`
- Pressure scenarios: [test-scenarios.md](test-scenarios.md)

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 source-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 source-work-order?

CallGet help
Cite this page

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