Prompts

The full index

38 prompts, each with receipts

• Scope controlexperimental

  Declare the change-set before you touch anything

  Use when an agent's diffs keep arriving with helpful extras you did not ask for.

  Copy promptRead it first →
• Divergence gate

  Explore, don’t decide: widen the field before the model converges

  Use in the moment before you ask a model to recommend, so the first plausible answer cannot anchor you.

  Copy promptRead it first →
• Onboarding

  Map an unfamiliar repo from evidence, not guesses

  Use on day one in a repo you have never seen and cannot yet trust anyone's summary of.

  Copy promptRead it first →
• Refactor

  Refactor under a net – pin the behaviour, then change it

  Use before refactoring code that has no tests and real users.

  Copy promptRead it first →
• Spec

  Turn a vague request into a spec, with every assumption tagged

  Use when the request is one line and the expensive decisions are all unstated.

  Copy promptRead it first →
• Performance

  Measure first – find the real bottleneck, keep only proven wins

  Use when something is slow and everyone already has a theory about why.

  Copy promptRead it first →
• Debugging

  No fix until the bug reproduces

  Use when an agent keeps offering fixes for a bug nobody has reproduced.

  Copy promptRead it first →
• Git workflow

  Git hygiene and work-recovery sweep

  Use when real work is stranded in stashes, stale branches, and orphaned worktrees.

  Copy promptRead it first →
• Fix verification

  Prove the bug is gone, not just that CI went green

  Use when CI went green after a fix and that is all you know.

  Copy promptRead it first →
• Model migrationexperimental

  Field-test a model swap before you trust the changelog

  Use when you are about to point production at a different model.

  Copy promptRead it first →
• QA audit

  Vacuous-pass audit: find the checks that pass without checking

  Use when everything is green and you cannot say what any of it actually proved.

  Copy promptRead it first →
• Sign-off gate

  Sign-off gate: prove the claim or label it NOT RUN

  Use when an agent says done, passing, or safe to deploy, and you want the receipt.

  Copy promptRead it first →
• Review synthesis

  Two adversarial critics, you stay the judge (dedupe + keep uniques)

  Use when two models have reviewed the same work and you have to be the judge.

  Copy promptRead it first →
• QA review

  Multi-lens QA fan-out: five blind reviews, then triage

  Use when one review pass keeps rationalising away what another pass would catch.

  Copy promptRead it first →
• Verify before encode

  Claim-ladder gate: verify against the live source before you encode it

  Use before you write a remembered fact into a config, a guardrail, or a doc.

  Copy promptRead it first →
• Integrity auditexperimental

  Audit a byte-exact copy-paste claim end to end

  Use when a copy button, an export, or a docs snippet hands people something subtly different from the source.

  Copy promptRead it first →
• Code review

  A code reviewer that refuses to rubber-stamp

  Use when reviews keep coming back approved with nothing said.

  Copy promptRead it first →
• PR review

  Cherry-pick the value from every PR (never merge dirty)

  Use when open PRs have piled up and each has one good part inside a mess.

  Copy promptRead it first →
• Governance auditexperimental

  Audit a deny-list from the threat, not from the list

  Use when a deny-list has grown by accretion and nobody knows what it misses.

  Copy promptRead it first →
• Safety auditexperimental

  Audit the fix you just made to a guardrail

  Use when you have patched a guardrail and nobody has checked the patch.

  Copy promptRead it first →
• Impact analysisexperimental

  Walk the blast radius before you touch shared code

  Use before editing something more than one place depends on.

  Copy promptRead it first →
• Optimisation

  Audit your governance, then level it up (enforced, not theatre)

  Use when a project has rules and gates and nobody has checked whether any of them fire.

  Copy promptRead it first →
• Abstain

  Abstain when the data is stale: suppress, do not guess

  Use when something reports confidently on data that may be stale, thin, or missing.

  Copy promptRead it first →
• Data safety

  Plan, then apply – a two-phase gate for irreversible actions

  Use before anything you cannot undo: a delete, a migration, a force-push, a deploy.

  Copy promptRead it first →
• Audit guard

  Audit guard: stop agents fixing work you deliberately deferred

  Use before any quick-wins or tech-debt sweep in a repo with documented deferrals.

  Copy promptRead it first →
• Safety audit

  Fail-open or fail-closed: audit a gate before you approve it

  Use when reviewing a guard and nobody can say what it does when it errors.

  Copy promptRead it first →
• Session reviewexperimental

  Self-score a work session where the score is disposable

  Use at the end of a session, when you want the corrections rather than the compliment.

  Copy promptRead it first →
• Dispatch contract

  Builder-lane dispatch: brief a second agent, judge its work

  Use when you are handing real code to a second agent and you will judge the result.

  Copy promptRead it first →
• Agent dispatch

  Brief a sub-agent like a colleague, not a warrant

  Use when a sub-agent follows your instructions to the letter and still misses the point.

  Copy promptRead it first →
• Agent ops

  Unattended autonomous work orchestrator: validate, then implement

  Use before a long run you will not be watching.

  Copy promptRead it first →
• Session handoff

  Session handoff and durable maintenance, double-audited

  Use at the end of a session a stranger has to pick up cold tomorrow.

  Copy promptRead it first →
• Agent ops

  Keep a long agent run from rotting

  Use when a run is long enough that the agent's own context is the thing degrading.

  Copy promptRead it first →
• Conformanceexperimental

  Make it look like the code already there

  Use when agent code works but reads like it arrived from a different codebase.

  Copy promptRead it first →
• Review pass

  Think Like Roy review pass: score work against a standard it must cite

  Use when a screen passes review and still feels generic, and you want the objection named.

  Copy promptRead it first →
• UI review

  AI-feel block audit: five laws before a screen ships

  Use when a screen looks fine block by block and reads AI-made as a whole.

  Copy promptRead it first →
• Writing

  Sharp engineering writer: four self-critiques that kill AI tells

  Use when the draft is technically right and reads like a model wrote it.

  Copy promptRead it first →
• Product/UX review

  Module-by-module product and UX review

  Use when the product works and you have not walked it as a user in months.

  Copy promptRead it first →
• agent I/O audit

  Verification-channel audit: find what rewrites your evidence

  An agent asserts "done", "passed" or "identical" and any compression, truncation or summarising layer sits between its tools and the model.

  Copy promptRead it first →

Nothing matches that. Try the jobs above, or read the index at /prompts.json.