engram-cogitator

Use when changing cogitation project settings (test/build/lint commands, branching conventions, graphify/codex toggles), or the user says "change config", "update settings", or "set test command"

Use when setting up a project for cogitation for the first time, or the user says "set up cogitation", "init", or "configure this project"

Use at the start of any conversation — establishes the cogitation workflow and requires invoking the right skill before responding, including before clarifying questions

Use for MEDIUM-sized work — new but contained behavior (one component, no architecture/data/API change) that deserves rigor without the design-doc + plan-doc ceremony of brainstorming

Use when the user wants to tailor the cogitation workflow — says "customise", "recustomise", "change the workflow", "make TDD less strict", "turn off finishing-branch", or wants a skill looser or disabled

Use when EC memories need cleanup — deduping, pruning stale entries, hygiene — or the user says "audit memories", "clean up EC", or "review what's stored"

Use before any feature work or new feature — interviews you about the feature one question at a time, pushes back on gaps, and saves a design doc with a decisions log

Use when you want an independent second-opinion review of a design doc or implementation plan from OpenAI Codex before executing — only if codex is enabled in .cogitation/config.json

Use when encountering a bug, test failure, or unexpected behavior and you need to find root cause before fixing

Use when you have a written plan in docs/plans/ ready to implement — runs every task continuously via TDD red-green-refactor, then reviews

Use when implementation is complete and a feature branch is ready to wrap up and merge

Use at the start of a session on an existing project, when joining a project, or the user says "catch me up", "what do I need to know", or "onboard me"

Use when facing 2+ independent tasks that can run concurrently — separate test failures, unrelated bugs, or parallelizable work

Use when processing code review feedback or PR comments — verify against the codebase before implementing, push back with reasoning when the feedback is wrong

Use when the user says "remember this", "store this", "save for later", or "don't forget", or after a decision, gotcha, or recurring pattern worth persisting to EC

Use when a diff is large or high-risk and Tier 0 inline self-review isn't enough — dispatches an independent reviewer subagent

Use when writing any code — implementing a feature, fixing a bug, adding functionality, or any change that should be test-first (the default for all implementation work)

Use before claiming tests pass, a build succeeds, or a bug is fixed

Use after brainstorming, when an approved design is ready to turn into a TDD-first implementation plan

Use when adding a new cogitation skill or workflow to the skill set