Independently audit a brownfield onboarding transcript, operational map, or exact proposed documentation patch before application. Use when a fresh reviewer must verify an $onboard-repository first pass, distinguish environment-caused Unknowns from reasoning defects, score its safety and evidence gates, or run a…
Convert accepted repository rules into the smallest repository-native mechanical validation with positive and negative proof and precise enforcement-level reporting. Use for requests to enforce architecture, reliability, security, or quality boundaries; prevent a documented violation from recurring; add structural…
Provide an explicitly requested, repository-grounded engineering review using contextual heuristics for code clarity, SOLID and design, testing, refactoring, architecture, and professional practice. Use only when the user invokes $engineering-wisdom or explicitly asks for this installed engineering-wisdom pack; do not…
Run one explicitly authorized, evidence-backed improvement to a repository's agent guidance, tools, runbooks, or validation. Use only when the user invokes $improve-harness or explicitly asks to improve the Harness after observed reusable agent friction. Do not use for ordinary product changes, speculative cleanup…
Inspect an unfamiliar or brownfield repository, trace one real operational path, and propose evidence-backed improvements that help future agents work independently. Use when explicitly asked to onboard, map, assess, or backfill agent-facing repository guidance; use again after the user approves exact proposal items.…
Turn vague ideas into verifiable Codex goals. Use when the user mentions goal mode, /goal, creategoal, autonomous work, or asks for an interview before goal creation.
Upgrade raw prompts into execution-ready instructions. Use when asked to improve a prompt, add context, tool, verification, or done rules, extract a template, or design an enhancement hook.
Build dependency-aware plans from goals, incidents, backlogs, or priorities. Use when priority conflicts with execution order and Codex must test prerequisites or mitigations, preserve absorbed-work traceability, or explain why lower-priority work happens first.
Organize an existing Git tree into logical commits and push them. Use when asked to commit everything, smart commit, group changes, clean the commit stack, or push work.
Create, inspect, edit, persist, and verify tldraw canvases through the tldraw Desktop local Canvas API without mouse-driven Computer Use. Use for scripted .tldraw diagrams, architecture drawings, flowcharts, canvas cleanup, bound connectors, screenshots, document scripts, or requests to automate an installed tldraw…
Research unfamiliar implementation work before coding. Use when work is ambiguous, version-sensitive, or risky and requires repo mapping, local reuse, upstream patterns, or current docs.
AGENTS.md instructions for hoangnb24/better-agents-md, covering mcp agent mail: coordination for multi-agent workflows, integrating with br (beadsrust), using bv as an ai sidecar, the workflow: start with triage and other commands.