Skip to content

DataArt/artisyn-implementation-harness / skills/implementation-harness

implementation-harness

Flagged

Install the portable AI-dev harness, rebuild its operational graph standalone, harvest project skill improvements into its canonical templates, package direct canonical edits into a portable bundle, or apply canonical updates to an existing project. Use /implementation-harness launch, /implementation-harness reindex-graph, or /implementation-harness patch harvest|prepare|apply.

FileKindSize
CHANGELOG.mdmarkdown37.5 KB
README.mdmarkdown13.7 KB
SKILL.mdskill md9.6 KB
bin/artisyn-implementation-harness.mjsexecutablescript11.8 KB
bin/lib/placer.mjsscript2.6 KB
bin/lib/providers.mjsscript1.8 KB
bin/lib/reporter.mjsscript3.0 KB
bin/lib/zip.mjsscript4.0 KB
canonical/adaptors/claude/browser.mdmarkdown2.5 KB
canonical/adaptors/claude/context.mdmarkdown517 B
canonical/adaptors/claude/credentials.mdmarkdown512 B
canonical/adaptors/claude/delegation.mdmarkdown910 B
canonical/adaptors/claude/interaction.mdmarkdown359 B
canonical/adaptors/claude/planning.mdmarkdown745 B
canonical/adaptors/claude/review.mdmarkdown1.0 KB
canonical/adaptors/claude/task-tracking.mdmarkdown897 B
canonical/adaptors/codex/browser.mdmarkdown1.0 KB
canonical/adaptors/codex/context.mdmarkdown517 B
canonical/adaptors/codex/credentials.mdmarkdown480 B
canonical/adaptors/codex/delegation.mdmarkdown910 B
canonical/adaptors/codex/interaction.mdmarkdown359 B
canonical/adaptors/codex/planning.mdmarkdown904 B
canonical/adaptors/codex/review.mdmarkdown973 B
canonical/adaptors/codex/task-tracking.mdmarkdown1.1 KB
canonical/adaptors/copilot/browser.mdmarkdown620 B
canonical/adaptors/copilot/context.mdmarkdown881 B
canonical/adaptors/copilot/credentials.mdmarkdown992 B
canonical/adaptors/copilot/delegation.mdmarkdown1.2 KB
canonical/adaptors/copilot/interaction.mdmarkdown454 B
canonical/adaptors/copilot/planning.mdmarkdown785 B
canonical/adaptors/copilot/review.mdmarkdown791 B
canonical/adaptors/copilot/task-tracking.mdmarkdown723 B
canonical/agents/architect/INTENT.mdmarkdown2.4 KB
canonical/agents/architect/TEMPLATE.mdmarkdown6.5 KB
canonical/agents/docs-writer/INTENT.mdmarkdown2.2 KB
canonical/agents/docs-writer/TEMPLATE.mdmarkdown2.8 KB
canonical/agents/infra/INTENT.mdmarkdown2.1 KB
canonical/agents/infra/TEMPLATE.mdmarkdown5.1 KB
canonical/agents/layer/INTENT.mdmarkdown6.0 KB
canonical/agents/layer/TEMPLATE.mdmarkdown1.5 KB
canonical/agents/onboarding/INTENT.mdmarkdown5.3 KB
canonical/agents/onboarding/TEMPLATE.mdmarkdown4.2 KB
canonical/agents/product-architect/INTENT.mdmarkdown7.5 KB
canonical/agents/product-architect/TEMPLATE.mdmarkdown3.9 KB
canonical/agents/scrum-master/INTENT.mdmarkdown10.9 KB
canonical/agents/scrum-master/TEMPLATE.mdmarkdown12.3 KB
canonical/docs/.og/cli.mjsscript13.6 KB
canonical/docs/.og/cli.test.mjsscript19.6 KB
canonical/docs/.og/constants.mjsscript2.9 KB
canonical/docs/.og/docs-operational-graph.sqlitebinary24.0 KB
canonical/docs/.og/docs.mjsscript5.5 KB
canonical/docs/.og/edges.mjsscript5.8 KB
canonical/docs/.og/schema.mjsscript741 B
canonical/docs/.og/utils.mjsscript5.2 KB
canonical/docs/Engineering Guide/01 Conventions.mdmarkdown3.0 KB
canonical/docs/Engineering Guide/03 Engineer Role.mdmarkdown2.6 KB
canonical/docs/Engineering Guide/04 AI Coding Tool Compatibility.mdmarkdown3.6 KB
canonical/docs/Engineering Guide/05 MCP Setup.mdmarkdown6.6 KB
canonical/docs/Engineering Guide/Documentation/01 Principles.mdmarkdown15.3 KB
canonical/docs/Engineering Guide/Documentation/02 Structure.mdmarkdown3.8 KB
canonical/docs/Engineering Guide/Documentation/03 HLD Intent.mdmarkdown8.1 KB
canonical/docs/Engineering Guide/Documentation/04 LLD Intent.mdmarkdown9.7 KB
canonical/docs/Engineering Guide/Documentation/05 NFR Intent.mdmarkdown6.0 KB
canonical/docs/Engineering Guide/Documentation/07 Terminology.mdmarkdown1.4 KB
canonical/docs/Engineering Guide/Lifecycles/00 Overview.mdmarkdown5.8 KB
canonical/docs/Engineering Guide/Lifecycles/01 Dev Lifecycle.mdmarkdown19.9 KB
canonical/docs/Engineering Guide/Lifecycles/02 Design Lifecycle.mdmarkdown29.4 KB
canonical/docs/Engineering Guide/Lifecycles/03 Evolve Lifecycle.mdmarkdown7.0 KB
canonical/docs/Engineering Guide/Lifecycles/04 Architecture Lifecycle.mdmarkdown3.6 KB
canonical/docs/Engineering Guide/Lifecycles/05 Documents Flow.mdmarkdown9.5 KB
canonical/manifest.jsonconfig1.6 KB
canonical/mcp.jsonconfig23 B
canonical/root-instructions/INTERFACE.mdmarkdown3.3 KB
canonical/settings.jsonconfig332 B
canonical/skills/design/INTENT.mdmarkdown28.6 KB
canonical/skills/design/TEMPLATE.mdmarkdown19.0 KB
canonical/skills/design/interfaces/architecture.mdmarkdown2.8 KB
canonical/skills/design/interfaces/contract.mdmarkdown7.4 KB
canonical/skills/design/interfaces/design.mdmarkdown2.3 KB
canonical/skills/design/interfaces/efforts.mdmarkdown2.5 KB
canonical/skills/design/interfaces/stack.mdmarkdown1.6 KB
canonical/skills/design/patterns/announce-progress.mdmarkdown997 B
canonical/skills/design/patterns/approval-intelligent.mdmarkdown1.5 KB
canonical/skills/design/patterns/approval-sign-off.mdmarkdown2.4 KB
canonical/skills/design/patterns/context-resolution.mdmarkdown6.6 KB
canonical/skills/design/patterns/design-architect-review.mdmarkdown2.4 KB
canonical/skills/design/patterns/design-oq-triage.mdmarkdown3.8 KB
canonical/skills/design/patterns/design-quality-gate.mdmarkdown1.4 KB
canonical/skills/design/patterns/do-report-commit.mdmarkdown1.2 KB
canonical/skills/design/patterns/docs-writer-authoring.mdmarkdown3.6 KB
canonical/skills/design/patterns/metrics.mdmarkdown11.9 KB
canonical/skills/design/patterns/multi-decision-split.mdmarkdown3.6 KB
canonical/skills/design/patterns/phase-sign-off.mdmarkdown2.4 KB
canonical/skills/design/patterns/satellite-review.mdmarkdown1.5 KB
canonical/skills/design/patterns/session-continuity.mdmarkdown827 B
canonical/skills/design/patterns/task-tracking.mdmarkdown779 B
canonical/skills/design/patterns/waf-review.mdmarkdown4.2 KB
canonical/skills/design/patterns/write-confirm.mdmarkdown963 B
canonical/skills/design/references/00-decision-router.mdmarkdown3.8 KB
canonical/skills/design/references/00-router.mdmarkdown4.6 KB
canonical/skills/design/references/01-context-gathering.mdmarkdown8.1 KB
canonical/skills/design/references/02-ceremony.mdmarkdown4.6 KB
canonical/skills/design/references/03-frame.mdmarkdown6.7 KB
canonical/skills/design/references/04-research.mdmarkdown8.1 KB
canonical/skills/design/references/05-evaluate.mdmarkdown9.0 KB
canonical/skills/design/references/06-solution.mdmarkdown13.7 KB
canonical/skills/design/references/07-review-gate.mdmarkdown4.1 KB
canonical/skills/design/references/08-address-feedback.mdmarkdown8.0 KB
canonical/skills/design/references/09-publish.mdmarkdown8.9 KB
canonical/skills/design/references/10-completion.mdmarkdown7.4 KB
canonical/skills/design/scripts/constants.mjsscript2.0 KB
canonical/skills/design/scripts/design-metrics.mjsscript35.4 KB
canonical/skills/design/scripts/design-metrics.test.mjsscript12.0 KB
canonical/skills/design/scripts/utils.mjsscript3.1 KB
canonical/skills/design/templates/evaluate.mdmarkdown1.4 KB
canonical/skills/design/templates/frame.mdmarkdown2.6 KB
canonical/skills/design/templates/report.mdmarkdown4.8 KB
canonical/skills/design/templates/research.mdmarkdown2.4 KB
canonical/skills/design/templates/stat.jsonconfig1.7 KB
canonical/skills/design/templates/stat.schema.jsonconfig17.1 KB
canonical/skills/dev/INTENT.mdmarkdown15.9 KB
canonical/skills/dev/TEMPLATE.mdmarkdown9.0 KB
canonical/skills/dev/interfaces/intent.mdmarkdown2.6 KB
canonical/skills/dev/patterns/announce-progress.mdmarkdown1.1 KB
canonical/skills/dev/patterns/approval-intelligent.mdmarkdown1.5 KB
canonical/skills/dev/patterns/approval-sign-off.mdmarkdown1.9 KB
canonical/skills/dev/patterns/do-report-commit.mdmarkdown888 B
canonical/skills/dev/patterns/metrics.mdmarkdown17.7 KB
canonical/skills/dev/patterns/phase-sign-off.mdmarkdown2.2 KB
canonical/skills/dev/patterns/review-gate.mdmarkdown3.6 KB
canonical/skills/dev/patterns/satellite-review.mdmarkdown3.1 KB
canonical/skills/dev/patterns/session-continuity.mdmarkdown797 B
canonical/skills/dev/patterns/task-tracking.mdmarkdown766 B
canonical/skills/dev/patterns/write-confirm.mdmarkdown615 B
canonical/skills/dev/references/00-router.mdmarkdown2.2 KB
canonical/skills/dev/references/01-context-gathering.mdmarkdown10.3 KB
canonical/skills/dev/references/02-ceremony.mdmarkdown4.5 KB
canonical/skills/dev/references/03-plan.mdmarkdown14.2 KB
canonical/skills/dev/references/04-implement.mdmarkdown11.7 KB
canonical/skills/dev/references/05-test.mdmarkdown7.8 KB
canonical/skills/dev/references/06-document.mdmarkdown11.7 KB
canonical/skills/dev/references/07-completion.mdmarkdown6.3 KB
canonical/skills/dev/scripts/constants.mjsscript3.2 KB
canonical/skills/dev/scripts/quality.mjsscript9.1 KB
canonical/skills/dev/scripts/quality.test.mjsscript6.6 KB
canonical/skills/dev/scripts/timing.mjsscript38.1 KB
canonical/skills/dev/scripts/timing.test.mjsscript21.0 KB
canonical/skills/dev/scripts/utils.mjsscript3.1 KB
canonical/skills/dev/templates/plan.mdmarkdown3.3 KB
canonical/skills/dev/templates/report.mdmarkdown6.4 KB
canonical/skills/dev/templates/stat.jsonconfig1.4 KB
canonical/skills/dev/templates/stat.schema.jsonconfig29.3 KB
canonical/skills/evolve/INTENT.mdmarkdown1.6 KB
canonical/skills/evolve/TEMPLATE.mdmarkdown1.3 KB
canonical/skills/evolve/interfaces/improvement.mdmarkdown1.2 KB
canonical/skills/evolve/interfaces/reflection.mdmarkdown353 B
canonical/skills/evolve/interfaces/validation.mdmarkdown653 B
canonical/skills/evolve/patterns/task-tracking.mdmarkdown787 B
canonical/skills/evolve/references/00-router.mdmarkdown1.1 KB
canonical/skills/evolve/references/01-reflect.mdmarkdown805 B
canonical/skills/evolve/references/02-triage.mdmarkdown2.6 KB
canonical/skills/evolve/references/03-draft.mdmarkdown1.2 KB
canonical/skills/evolve/references/04-validate.mdmarkdown1.5 KB
canonical/skills/evolve/references/05-adopt.mdmarkdown1.5 KB
canonical/skills/war/INTENT.mdmarkdown4.5 KB
canonical/skills/war/TEMPLATE.mdmarkdown1.8 KB
canonical/skills/war/patterns/present-and-save.mdmarkdown1.0 KB
canonical/skills/war/patterns/scope-resolution.mdmarkdown830 B
canonical/skills/war/references/01-design.mdmarkdown3.4 KB
canonical/skills/war/references/02-implementation.mdmarkdown3.8 KB
canonical/skills/war/templates/design-report.mdmarkdown869 B
canonical/skills/war/templates/implementation-report.mdmarkdown1.8 KB
canonical/skills/where-we-are/INTENT.mdmarkdown3.3 KB
canonical/skills/where-we-are/TEMPLATE.mdmarkdown6.3 KB
canonical/skills/where-we-are/report-template.mdmarkdown2.0 KB
canonical/skills/x-ray/INTENT.mdmarkdown2.4 KB
canonical/skills/x-ray/TEMPLATE.mdmarkdown10.5 KB
implementation-harness.mdmarkdown1.4 KB
package.jsonmanifest696 B
patch/20261105T160045Z-3.3.0-copilot-provider-6630df3d-f6bf-4651-8732-8048942ad1fe/diffs/CHANGELOG.md.patchother1.2 KB
patch/20261105T160045Z-3.3.0-copilot-provider-6630df3d-f6bf-4651-8732-8048942ad1fe/diffs/README.md.patchother1.9 KB
patch/20261105T160045Z-3.3.0-copilot-provider-6630df3d-f6bf-4651-8732-8048942ad1fe/diffs/SKILL.md.patchother2.5 KB
patch/20261105T160045Z-3.3.0-copilot-provider-6630df3d-f6bf-4651-8732-8048942ad1fe/diffs/canonical/agents/docs-writer/INTENT.md.patchother1.4 KB
patch/20261105T160045Z-3.3.0-copilot-provider-6630df3d-f6bf-4651-8732-8048942ad1fe/diffs/canonical/docs/.og/cli.test.mjs.patchother846 B
patch/20261105T160045Z-3.3.0-copilot-provider-6630df3d-f6bf-4651-8732-8048942ad1fe/diffs/canonical/docs/Engineering Guide/04 AI Coding Tool Compatibility.md.patchother3.4 KB
patch/20261105T160045Z-3.3.0-copilot-provider-6630df3d-f6bf-4651-8732-8048942ad1fe/diffs/canonical/docs/Engineering Guide/05 MCP Setup.md.patchother5.2 KB
patch/20261105T160045Z-3.3.0-copilot-provider-6630df3d-f6bf-4651-8732-8048942ad1fe/diffs/canonical/manifest.json.patchother662 B
patch/20261105T160045Z-3.3.0-copilot-provider-6630df3d-f6bf-4651-8732-8048942ad1fe/diffs/canonical/settings.json.patchother150 B
patch/20261105T160045Z-3.3.0-copilot-provider-6630df3d-f6bf-4651-8732-8048942ad1fe/diffs/canonical/skills/design/INTENT.md.patchother19.4 KB
patch/20261105T160045Z-3.3.0-copilot-provider-6630df3d-f6bf-4651-8732-8048942ad1fe/diffs/patterns/skill-authoring.md.patchother692 B
patch/20261105T160045Z-3.3.0-copilot-provider-6630df3d-f6bf-4651-8732-8048942ad1fe/diffs/references/host-capabilities.md.patchother1.2 KB
patch/20261105T160045Z-3.3.0-copilot-provider-6630df3d-f6bf-4651-8732-8048942ad1fe/diffs/references/launch/01-launch.md.patchother1.1 KB
patch/20261105T160045Z-3.3.0-copilot-provider-6630df3d-f6bf-4651-8732-8048942ad1fe/diffs/references/launch/01a-launch-plan.md.patchother1.6 KB
patch/20261105T160045Z-3.3.0-copilot-provider-6630df3d-f6bf-4651-8732-8048942ad1fe/diffs/references/launch/01b-launch-install.md.patchother7.3 KB
patch/20261105T160045Z-3.3.0-copilot-provider-6630df3d-f6bf-4651-8732-8048942ad1fe/diffs/references/launch/02-launch-questions.md.patchother5.2 KB
patch/20261105T160045Z-3.3.0-copilot-provider-6630df3d-f6bf-4651-8732-8048942ad1fe/diffs/references/launch/08-provider-launch.md.patchother3.2 KB
patch/20261105T160045Z-3.3.0-copilot-provider-6630df3d-f6bf-4651-8732-8048942ad1fe/diffs/references/patch/04-patch-harvest.md.patchother2.6 KB
patch/20261105T160045Z-3.3.0-copilot-provider-6630df3d-f6bf-4651-8732-8048942ad1fe/diffs/references/patch/05-patch-apply.md.patchother3.0 KB
patch/20261105T160045Z-3.3.0-copilot-provider-6630df3d-f6bf-4651-8732-8048942ad1fe/diffs/references/patch/06-patch-state.md.patchother7.1 KB
patch/20261105T160045Z-3.3.0-copilot-provider-6630df3d-f6bf-4651-8732-8048942ad1fe/diffs/scripts/lib/agent-format.mjs.patchother2.2 KB

canonical/skills/dev/references/04-implement.md

View on GitHub
# Implement stage

Apply `{{provider:skills_root}}/dev/patterns/metrics.md`; this stage's metrics unit is
`--stage implement`. First actions: mark this stage's native task `in_progress`
(`patterns/task-tracking.md`), then `stage start --stage implement`.

Routing and stage tracking live in `{{provider:skills_root}}/dev/SKILL.md`. This stage
executes the approved `1-plan.md` one step at a time.

Two stops in this stage: the sign-off in Step 4 (`patterns/phase-sign-off.md`) and the
commits by block in Step 6. Report sits between them.
Each step ends with an intelligent checkpoint (Step 3), not a stop. Stop mid-phase
only when a step genuinely needs the developer: a check only they can do, a guarded
command, or a divergence from the plan.

> ๐Ÿ” **After context compaction:** re-read this file and run metrics `recover`
> before recording anything (`patterns/session-continuity.md`). Fresh vs. resume was
> already decided by the router's entry check; do not redo completed work.

## Step 1 โ€” Read the plan

`$IMPL_DIR` comes from the router's entry check. If `1-plan.md` is not in it, Plan has
not run: say so and stop.

Read the full `1-plan.md` first. Also open `2-report.md`; all notes, tech debt and
status go there. **Never edit `1-plan.md`.**

Read open and accepted deviations in `## Review Findings`. For legacy plans, import
their exceptions once with source references and deduplicate against existing RF
rows. Do not copy a second live table into the report.

## Step 2 โ€” Advance phase and track steps

Update the `Phase` row in `2-report.md`:

```
๐ŸŽฏ Context โœ… ยท ๐Ÿš€ Ceremony โœ… ยท ๐Ÿ“‹ Plan โœ… ยท ๐Ÿ”จ Implement ๐Ÿ”„ ยท ๐Ÿงช Test โณ ยท ๐Ÿ“ Document โณ ยท ๐Ÿ Completion โณ
```

Apply `{{provider:skills_root}}/dev/patterns/task-tracking.md` with the plan's numbered
steps as the unit list: one task per step, in plan order, as children of the
stage-level Implement task the router created.

Announce the plan and step count, then start.

## Step 3 โ€” Execute one step at a time

Before each step, match its target paths against the Agents table in
`{{provider:instructions_file}}` and the installed role definitions. Use the
specialist that owns the component; there is no fixed frontend/backend/data list.
Give it the full step from `1-plan.md` and the current `2-report.md`. Apply
runtime/delegation.md; you own verification and the report.

If no specialist owns the scope, implement inline. Resolve ambiguous ownership
before dispatch. For a cross-component step, give each owner a disjoint scope and
coordinate shared contracts yourself.

> **Scope discipline:** implement exactly what the step says. No extra features,
> refactors or improvements.

For each step:

1. **Register and start.** `step add` (stable ID, title, order, plan reference),
   then `step start --id <ID>`. Mark the step's task `in_progress`. Say which step
   you are starting and whether you delegate or implement inline.

2. **Implement (or delegate).** Workers run a satellite review after non-trivial
   steps before returning (`{{provider:skills_root}}/dev/patterns/satellite-review.md`).
   When a worker returns, check the change actually landed (`git status`,
   `git diff`); a self-report is not evidence.

3. **Verify.** Run the step's verification items from the plan yourself: the
   commands, the curl, the file you inspect. Read the real output. For a check a
   worker already ran with real captured output, use that result instead of
   re-running blindly; re-run only for a reason (the worker lacked the tool, the
   environment differs, the result looks off). Never run a guarded command; that
   item goes to the developer in the checkpoint below. For a test-first step, the
   expected result is red for the stated reason; later steps rerun the same suite
   until green.

   **Record the evidence** (`patterns/metrics.md`), separately from running it:

   - A command you run โ†’ wrap it so the real exit status is stored:
     `check --id step-NN-<kind>-run-01 --kind <build|test|lint|typecheck> --name "<what>" -- <command>`
   - A result you observed without a command, or a worker's captured run โ†’
     `check record --source self|worker --result passed|failed --evidence "<what you saw>"`
   - Never `--source developer` for anything the developer did not actually say in
     this conversation.

4. **Step checkpoint.** Intelligent-approval checkpoint
   (`patterns/approval-intelligent.md`). Auto-approval conditions, all required:

   - Every verification item in the plan for this step was something a command or
     your own inspection could answer, and all of them passed
   - The implementation matches the plan's description of the step; any narrowing
     or growth of scope is small and already noted in the report
   - Nothing in the step is UI/UX-visible in a way the developer would want to see
     with their own eyes
   - No guarded command and no credential or access you lack is needed to verify it

   All met โ†’ `step complete --id <ID>`, then do items 5 and 6 below, say in one line
   that the step checkpoint passed and what you ran, and start the next step.

   Any condition fails or is uncertain โ†’ stop and ask the developer for exactly the
   missing piece. Report what you ran and the real result; name the divergence or
   the item that needs their eyes; give the precise action (what to open, what to
   look at, which command to run). Do not ask a general "does it look good?".
   A verification item that needs a live browser applies
   `{{provider:skills_root}}/dev/runtime/browser.md`. If the browser tools report not
   connected, follow that file's "When the tools are not exposed" walkthrough once
   (say what is missing and how to connect) before handing the check to the
   developer; record it as verified by them, their words as evidence.
   Before stopping: update the step's Progress row and note, `report`, then
   `wait start --reason user_input --detail "Step N: <what is needed>"`.
   **Stop and wait.** On the reply, `resume --activity implementation` and record
   their answer as an acceptance check with `--source developer` and their words as
   evidence. Passed โ†’ `step complete`. Failed โ†’ `step retry --id <ID> --reason verification_failure`,
   fix, verify again, come back to this checkpoint.

5. **Report.** Follow `patterns/do-report-commit.md`: update `2-report.md` before any
   commit message, in this order:

   - Progress row โ†’ `โœ… Done`, a short note in Notes (what landed, anything unusual),
     Test and Docs empty
   - `### Step N โ€” {title}` at the **bottom** of `## Implementation Notes`. One line
     when it went as planned. A full incident record when it needed troubleshooting:
     initial error, each hypothesis ruled out, root cause, fix. "Fixed and resolved"
     is not acceptable after a troubleshooting chain. Remove the placeholder line
     before inserting `### Step 1`.
   - Keep notes in ascending step order.
   - Mark the step's task `completed`.

6. **Announce** (`patterns/announce-progress.md`): what landed, what verified it,
   what is next. Commits are proposed once, by block, at the end of the phase
   (Step 6); do not stop for one here.

> โš ๏ธ **Never commit yourself.** Do not run `git add` or `git commit`. Other local,
> reversible git operations (`git mv` in Completion)
> are fine. Follow the project's guarded-command rules for everything else.

### While working on a step: external blockers

If a step cannot finish because of an external dependency (IT request, missing
permission, network policy, missing secret):

1. **Do not stop.** Continue with steps that do not depend on it
2. Add a `## Tech Debt` row with type `blocker`: what is blocked and why, the exact
   action required (command, request text, who to contact), what to do once resolved
3. Note it under the step in `## Implementation Notes`
4. Tell the developer: "Step N is blocked on `{reason}`. Logged in 2-report.md, continuing with unblocked steps."

### While working on a step: tech debt

If you find something that should be done but is out of scope, do not do it. Add a
`## Tech Debt` row and mention it in one line: "Added TD-N to tech debt: `{title}`".

| #    | Description           | Type     | Tracker | Finding    | Owner             | Next action        |
| ---- | --------------------- | -------- | ------- | ---------- | ----------------- | ------------------ |
| TD-N | What and why deferred | `{type}` | โ€”       | RF-ID or โ€” | Responsible owner | Concrete next step |

Valid types: `blocker` ยท `dependency` ยท `cleanup` ยท `security` ยท `performance` ยท `ux`

### While working on a step: failures

When a check fails or the developer reports an error:

- Diagnose the root cause before changing anything
- Fix only what is broken; do not refactor around it
- Re-run the same named check
- Do not move to the next step until this one passes

## Step 4 โ€” Sign-off (rework if any)

When every step is complete, apply `patterns/phase-sign-off.md`. Present:

- Each step in one line: what landed, what verified it (self / worker / developer),
  the result
- Steps that were auto-approved, and the one-line reason each
- Any divergence from the plan, named explicitly
- Anything the developer should look at themselves before Test (UI, a flow on
  their machine) that did not already stop the phase, as a precise action

> "All {N} steps implemented. {Summary above.} Good to move to Test?"

`report`, then `wait start --reason approval --detail "Awaiting implement sign-off"`.
**Stop and wait.** No reply, no next step. On approval, record the acceptance check
(`--name "Implement sign-off"`, `--source developer`, their words as evidence); without
it `stage complete` is refused.

Rework: `step retry --id <ID> --reason review_feedback` for the affected step, fix,
re-verify through Step 3, present again.

## Step 5 โ€” Report

Update `2-report.md`:

1. **Progress table** โ€” final pass, nothing stale
2. **Delivery Summary** โ€” only if the ticket deserves a human-readable summary
   (significant feature, complex refactor, something a reviewer benefits from).
   One short paragraph between the Progress table and Implementation Notes.
3. **Tech Debt** โ€” anything found at wrap-up. Flag debt that blocks acceptance
   criteria; it cannot be silently deferred. Any authorised scope addition needs a
   plan addendum and new progress rows; the original plan stays as is.
4. **Efforts Spent** โ€” one summary row if useful
5. `Phase` row โ†’ `๐ŸŽฏ Context โœ… ยท ๐Ÿš€ Ceremony โœ… ยท ๐Ÿ“‹ Plan โœ… ยท ๐Ÿ”จ Implement โœ… ยท ๐Ÿงช Test ๐Ÿ”„ ยท ๐Ÿ“ Document โณ ยท ๐Ÿ Completion โณ`

Then metrics `report`.

## Step 6 โ€” Commit, by block

One commit per step, or per logical block when several small steps belong together,
in plan order, each with its files:

> "Commits, in order:
>
> 1. `feat(infra): provision managed identity and key vault` โ€” `apps/infra/...`
> 2. `feat(auth): add basic auth header validation` โ€” `apps/lambda-auth/...`
> 3. `docs({ticket-lowercase}): update implementation report` โ€” `impl/2-report.md`, `impl/stat.json`
>
> Let me know when they're in."

Conventional Commits: `{type}({scope}): {description}`, lowercase, imperative, no
period. Types: `feat`, `fix`, `chore`, `refactor`, `docs`, `test`, `ci`, `build`.
Scope: the {{BUILD_UNIT_LABEL}} name or layer. No body unless breaking. A commit
that would need two types to be honest means the block is too broad; split it.

This is a manual-operation sign-off (`patterns/approval-sign-off.md`): the developer
runs the commit, you wait. `wait start --reason user_input --detail "Awaiting commit"`.
**Stop and wait.** On the reply, check `git log`/`git status`: the commit exists and the
worktree holds nothing from this phase. If not, say what is missing and wait again.
Then `stage complete --stage implement`.

๐Ÿ” Re-read `{{provider:skills_root}}/dev/SKILL.md` and resume the router from the next stage (Test).
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why โ€” repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" โ€” or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself โ€” your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall