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/design/patterns/approval-sign-off.md
View on GitHub# Sign-off
A **sign-off** is a stop-and-wait gate: the developer must explicitly approve
content, personally run a manual operation, or confirm an out-of-band decision,
before the lifecycle proceeds. It blocks progress until an explicit reply; silence,
a later unrelated message, or an automated notification is never a sign-off.
The lifecycle uses sign-offs sparingly. The normal place is the end of a phase
(`patterns/phase-sign-off.md`). Steps inside a phase use intelligent checkpoints
(`patterns/approval-intelligent.md`) and keep going when the content qualifies —
anything they would have asked about is carried into the phase sign-off instead.
A step that still names itself a sign-off gate outside that shape — a manual
operation, an external confirmation, a free-form input only the developer can
supply — is a human checkpoint by design: that stop is unconditional, never
skipped, downgraded to an announcement, or weakened by routine-work authorization
— however small it looks. Whether a given step requires a sign-off, and which
kind, is a decision made at that step, not by this pattern; changing it is its own
explicit edit, called out on its own, never a side effect of an unrelated change.
Three common shapes:
- **Content sign-off** — the developer reviews a drafted or persisted artifact and
confirms it. Present the actual content (in full if reasonably short, or a
faithful summary for a long artifact); a summary that omits what changed is not
a basis for approval. Present every item the developer needs to meaningfully
confirm, regardless of how many you already checked yourself.
- **Manual operation** — an action only the developer can run (branch checkout, a
commit, a guarded command). Propose the exact command and wait for them to run
it and confirm — never run it yourself, even once they've said yes.
- **External confirmation** — a fact only the developer can attest to (the MR was
approved, a manual check passed). This can never be inferred, self-certified, or
substituted by a WAF pass or a clean satellite review, however thorough those are
as evidence to report.
Running an available, non-guarded check yourself (re-reading a file, re-deriving a
table from data already confirmed) as a debugging aid is routine authorized work
and does not require asking first — but it never substitutes for the sign-off
itself. Report exactly what you checked, then still stop and wait for the specific
confirmation the gate needs.
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: 472k | 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 |