AI Agent Workflow Collection

Shapes turns action-first: action leads, steps numbered, state restated. Use for ADHD-friendly output. Do not use to trim tokens; use response-compression.

Track per-agent token usage and flag waste patterns in parallel dispatch workflows. Consult after running parallel agents to evaluate whether expenditure was proportional to value. Cross-references the plan-before-large-dispatch rule.

Models a business in its own language. Use when the domain has real business rules to capture.

Makes agent reasoning visible, surfaces tradeoffs, and fades help so humans build judgment. Use when reviewing or learning from agent-written code.

Explain plugin, skill, command, agent, and hook mechanics used here. Use when authoring or debugging plugins. Do not use for ops; use night-market-operations.

Provides sanitization guidelines for external content in skills and hooks. Use when loading GitHub Issues, PRs, WebFetch results, or any untrusted input.

Verifies a package exists before install, defending against hallucination and slopsquatting. Use when adding, recommending, or installing a package.

Computes DORA delivery-performance metrics from git and GitHub API. Use when assessing deployment frequency, lead time, or change failure rate.

Guide minimal code via a decision ladder with full safety, edge, and negative-case coverage. Use when adding code, choosing a dependency, or auditing a diff.

Ramps implementation ambition a notch only after the prior increment is understood. Use when building a feature you must understand, not just ship.

Decides hand-vs-compiler for loop transforms (unrolling, SIMD, fusion, hoisting). Use when reviewing/authoring a hot loop or tempted to hand-optimize one.

Probe memory/summary clarity via dual anchor questions: task progress, info gaps. Use when verifying session state or summary before handoff or compression.

States load-bearing decisions, invariants, and weak points. Use when judging a design change. Do not use for gating; use night-market-change-control.

Rebuild the dev environment: uv, Python tiers, pins, traps. Use when onboarding or toolchain breaks. Do not use for daily commands; use night-market-operations.

Classify, gate, and review changes. Use when landing a PR, releasing, or amending rules. Do not use for failure triage; use night-market-debugging-playbook.

Search and record project memory (Discussions, journal, ADRs). Use before re-investigating anything. Do not use for settled battles; see failure-archaeology.

Bind loop 'done' to unfakeable gates. Use to harden egregore/herald loops or promote completionintegrity. Not for QA gates; use night-market-validation-and-qa.

Catalog every config axis, its defaults and guards. Use when adding or auditing configuration. Do not use for running gates; use night-market-operations.

Triage night-market failures by symptom (hooks, CI, tests). Use when a check fails unexpectedly. Do not use for routine gates; use night-market-operations.

Run and interpret repo diagnostic scripts (ratchets, validators, token stats). Use when measuring health. Do not use to run tests; use night-market-operations.

Maintain docs of record, ADRs, changelog, and house style. Use when writing repo docs. Do not use for release steps; use night-market-operations instead.

Chronicles settled battles, reverts, and dead ends. Use when a fix echoes a past failure. Do not use for live triage; use night-market-debugging-playbook.

Run and ship this repo: make targets, artifacts, release runbook. Use when testing, linting, or releasing. Do not use for setup; use night-market-build-and-env.

Map open problems where this repo can advance SOTA. Use when scoping research. Do not use to run the campaign; use night-market-completion-integrity-campaign.