retro

The user has asked for a retrospective. You are suggesting improvements to the coding agent's environment to improve future runs.

Keep repository-wide failure prevention with correct. When session evidence suggests repeated code mistakes, report the examples and recommend that investigation. Use it directly when the user's request includes investigating or repairing that class; a retrospective alone remains recommendations.

Steps

1. Apply writing-for-agents for the writing style guide.
2. Read the primary sources for the session the user specifies; default to the current one. In T3 Code, prefer scoped t3_thread_read and t3_thread_search for app history and task receipts. Use local session logs when app history is unavailable or the requested session belongs to another host. Check current artifacts before treating a historical statement as the present state.
3. Look for candidates for improvement in these categories.

• Navigation: how easy was it for the agent to find the right files? Are there hidden dependencies between files? Would a navigation pointer make it easier? Use when the session took a long time to find a piece of information.
• Automated checks: are there automated checks that could catch errors the agent made? Linting, typing, tests, filesystem linters? Read the repo's own check command first (its package.json/build-tool lint/check scripts, its CI workflow), so a check that already exists but sits unwired or silently broken is the finding, not a reinvention. A repo with no guardrail (no pre-commit hook and no CI job running its lint/typecheck/test command) is itself a finding: an un-linted repo is a standing missed opportunity, not a neutral default. Use when the agent made a mistake an automated check could have caught, or the repo has no guardrail at all.
• Coding standards: should the reviewer agent be given a new rule to enforce? Should an existing rule be removed or clarified? Classify the violation first: a mechanical one (a fixed syntactic pattern, a banned API, an import shape, a file-location rule) gets a deterministic check, full stop: a custom rule in the repo's own linter, a new pre-commit hook, or a new CI job, whichever the repo's language and existing guardrail make cheapest. Default to building the check over writing the rule. Reserve CODING_STANDARDS.md for genuine judgement calls (cross-file consistency, "matches the surrounding style," anything no guardrail could ever substitute for). Use when the reviewer agent failed to catch a mistake.
• Global AGENTS.md: are there any steering instructions that should be moved to coding standards (or automated checks) instead? Use when the AGENTS.md file is particularly large - in the repo OR the user's global scope.
• Tool economy: did the agent make expensive tool calls that could be streamlined? Is there any custom tooling (CLI's, MCP's) that is particularly token-inefficient? Use when the agent made an expensive tool call.
• No-ops: look for instructions in steering files that don't modify the agent's behavior. Use when the steering files are large and unwieldy.
• Information access: look for opportunities to increase the agent's access to information. Teeing dev server logs, readonly access to third-party services. Use when a crucial piece of information was not available to the agent.

4. Present these candidates to the user, in order of severity, with the session evidence and proposed change for each. A retrospective produces recommendations; implement them only when the user has requested those changes.

Reference

Implementation vs Review

Remember that all work goes through two stages: implementation and review. The implementation agent has the most context pressure. They are responsible for exploration, writing code, and debugging failures.

The review agent receives the diff and relevant requirements. It can inspect surrounding code and contracts to assess the change, while leaving implementation and fixes to their owner.

Implementation follows the project's coding standards; independent review checks that they were applied.

Files

You have access to several files in the repo:

• CLAUDE.md/AGENTS.md: these files are pushed to the context window of any agent working in this repo. They should be used incredibly sparingly, usually only for navigation pointers to other files.
• CODING_STANDARDS.md: consult existing project standards during implementation and review. Add navigation pointers to docs folders if the standards file gets more than 1,000 lines long.
• Docs: use docs as references files, pointed to by other files. Look for existing docs before writing new ones.
• Skills: use skills for docs (since their description goes into the agent's context window), or for user-invoked commands. Follow the advice in the writing-for-agents skill.