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/adaptors/codex/task-tracking.md
View on GitHub# Progress in Codex
Use Codex's native `update_plan` TODO tool when it is exposed and permitted. Create
one plan item per shared work unit, then update it to `in_progress` before starting
the unit and `completed` only after verifying its completion evidence. Update the
plan after each transition; the tool supports `pending`, `in_progress`, and
`completed`, but has no dependency graph, so enforce stage order yourself. Mirror
every transition and its evidence in the durable launch report.
If `update_plan` is not exposed, use the report as the tracker. Before beginning a
stage, change its row to `In progress`; after verifying its outputs, mark it
`Complete` and record concrete evidence before starting the next stage. Update the
report after each stage boundary and immediately after recording a blocker. Do not
leave several finished stages marked pending while doing later-stage work.
Do not substitute `/plan` mode or a persistent Goal for the stage tracker. Record
failures and blocked dependencies in the report. Updating progress does not approve
work or change the plan's authorization boundaries.
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: 470k | 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 |