DataArt/artisyn-implementation-harness / skills/implementation-harness
implementation-harness
FlaggedInstall 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.
canonical/skills/dev/templates/report.md
View on GitHub---
name: Dev Report Template
description: Template for 2-report.md — the living implementation report created by {{provider:invoke:dev}} context and updated throughout the dev lifecycle
type: reference
---
# <TICKET>: <Short Title> — Report
| Field | Value |
| ------ | -------------------------------------------------------------------------------------------------------------- |
| Ticket | {{PROJECT_KEY}}-XX |
| Branch | — _(set by Ceremony, e.g. `feat/{{PROJECT_KEY}}-XX-slug`)_ |
| PR | — |
| Author | _from `git config user.name`_ |
| Status | 🔄 In Progress _(→ ✅ Complete, set by Completion)_ |
| Phase | 🎯 Context 🔄 · 🚀 Ceremony ⏳ · 📋 Plan ⏳ · 🔨 Implement ⏳ · 🧪 Test ⏳ · 📝 Document ⏳ · 🏁 Completion ⏳ |
## Progress
| # | Step | Status | Notes | Test | Docs |
| --- | ------------ | ---------- | ----- | ---- | ---- |
| 1 | _Step title_ | ⏳ Pending | | | |
<!--
Status values : ⏳ Pending · 🔄 Active · ✅ Done · ⚠️ Blocked · ⏭️ Skipped
Test / Docs : ✅ done · — not applicable · (empty) = not yet run
-->
## Stage Metrics
<!-- dev-metrics-stage:start -->
Source: [stat.json](stat.json). **Elapsed** = wall-clock time from the stage's first
start to its completion (includes any wait). **Work** = summed observed work
intervals (active effort) within that span. **Wait** = summed observed wait
intervals (blocked on developer input, approval, or an external dependency) within
that span. Work + Wait can read less than Elapsed when time went unclassified, or
more after a retry reopened the stage. Durations are shown as `Xh Ym Zs`, rounded to
the nearest second; open intervals are excluded from Elapsed/Work/Wait. Token
subtotals have unavailable coverage; ticket usage is not allocated to individual
units. **Flags** surfaces non-initial attempt triggers (🔁 retried/rework, 🔀 scope
change, 🔓 reopened) and any failed check (⚠️), derived from recorded data — never a
new judgment call — so a reader can scan for problem stages without parsing every row.
| Stage | Started (UTC) | Completed (UTC) | Elapsed | Work | Wait | Input tokens | Output tokens | Coverage | Attempts | Failed checks | Flags |
| ----- | ------------- | --------------- | ------- | ---- | ---- | ------------ | ------------- | -------- | -------- | ------------- | ----- |
<!-- dev-metrics-stage:end -->
## Step Metrics
<!-- dev-metrics-step:start -->
Source: [stat.json](stat.json). **Elapsed** = wall-clock time from the step's first
start to its completion (includes any wait). **Work** = summed observed work
intervals (active effort) within that span. **Wait** = summed observed wait
intervals (blocked on developer input, approval, or an external dependency) within
that span. Work + Wait can read less than Elapsed when time went unclassified, or
more after a retry reopened the step. Durations are shown as `Xh Ym Zs`, rounded to
the nearest second; open intervals are excluded from Elapsed/Work/Wait. Token
subtotals have unavailable coverage; ticket usage is not allocated to individual
units. **Flags** surfaces non-initial attempt triggers (🔁 retried/rework, 🔀 scope
change, 🔓 reopened) and any failed check (⚠️), derived from recorded data — never a
new judgment call — so a reader can scan for problem steps without parsing every row.
| Step | Started (UTC) | Completed (UTC) | Elapsed | Work | Wait | Input tokens | Output tokens | Coverage | Attempts | Failed checks | Flags |
| ---- | ------------- | --------------- | ------- | ---- | ---- | ------------ | ------------- | -------- | -------- | ------------- | ----- |
<!-- dev-metrics-step:end -->
## Review Findings
| ID | Stage | Origin | Kind | Deviation type | Severity | Classification | Finding | Evidence | Resolution | TD | Decision |
| --- | ----- | ------ | ---- | -------------- | -------- | -------------- | ------- | -------- | ---------- | --- | -------- |
<!-- One row per underlying issue; see patterns/review-gate.md. Empty means no recorded findings, not proof of review. -->
## Implementation Notes
_Added for every step — a brief confirmation for smooth steps, detailed notes for surprises, workarounds, or decisions made._
## Tech Debt
| # | Description | Type | Tracker | Finding | Owner | Next action |
| --- | ----------- | ---- | ------- | ------- | ----- | ----------- |
<!--
Type values: blocker · dependency · cleanup · security · performance · ux
Tracker: fill in once a task is created (e.g. {{PROJECT_KEY}}-XX), otherwise —
Rows are added here by the Implement stage (references/04-implement.md, tech debt while working on a step) as debt is discovered.
-->
## Test Results
| Project | Build | Tests | Typecheck | Lint | Written | Passed | Failed | Skipped | Evidence |
| ------- | ----- | ----- | --------- | ---- | ------- | ------ | ------ | ------- | -------- |
<!-- One row per non-overlapping project/suite scope, updated to its latest run.
Written = new test cases in this change, not files/assertions. Passed/Failed/Skipped
= latest runner case counts. Use unavailable when unknown, never infer counts from
exit status. Explicit 0 requires evidence; — is not measured. Evidence links runner
output and the diff supporting Written. Historical failed runs remain in stat.checks.
-->
## Documentation
| Doc / section | Tier | Action | Why | Done |
| ------------- | ---- | ------ | --- | ---- |
<!-- Written by the Document stage (references/06-document.md Step 3) before any doc
is touched; Done is ticked as @docs-writer returns each row. Tier is one from
Documentation/02 Structure.md. Action: new · updated · retired. Why points at the
plan Solution, an implementation note or an RF row. Empty means no doc impact was
identified, not that docs were skipped; say so in a line below the table. -->
## Efforts Spent
| Date | Phase | Human time | AI tokens | Notes |
| ---- | ----- | ---------- | --------- | ----- |
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — 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" — 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |