tdwhere123

tdwhere123/do-it

Plugin Claude Code

do-it meaning-centric marketplace for Claude Code: tier routing, write-time quality, focused review, and evidence-backed completion.

tdwhere123/do-it

Plugin Claude Code

Meaning-centric engineering plugin for Claude Code: tier routing, advisory write-quality, focused review, and evidence-backed completion.

tdwhere123/do-it

Instructions file CodexOpenCode

Instructions for tdwhere123/do-it, covering agents.md, file rules, repository, source of truth vs build artifacts and closed-set contracts.

tdwhere123/do-it

Command

A command that creates missing documentation templates in a project's `.do-it/handbook/` folder. The handbook is a small set of shared project notes, such as rules, design, terminology, and work-log templates.

tdwhere123/do-it

Command

A project command for turning local, privacy-filtered retrospective logging on or off, checking its status, or generating a review report.

tdwhere123/do-it

Command

一次性跳过 do-it 钩子（router / grill / verification-gate）。参数可选 grill / router / gate / all（默认 all）。.

tdwhere123/do-it

Hook

Runs when you submit a prompt, before the agent sees it, executing behavior-feedback.sh, prompt-submit.sh and subagent-stance.sh (3 commands). From tdwhere123/do-it.

tdwhere123/do-it

Hook

Runs to expand your prompt before the agent sees it for ^do-it-retrospective$ tool calls, executing behavior-feedback.sh. From tdwhere123/do-it.

tdwhere123/do-it

Hook

Runs before the agent uses a tool for Bash tool calls, executing strict-external-actions.sh (7 commands). From tdwhere123/do-it.

tdwhere123/do-it

Hook

Runs after a tool call finishes for Edit, Write, MultiEdit and NotebookEdit tool calls, executing write-quality-lint.sh. From tdwhere123/do-it.

tdwhere123/do-it

Hook

Runs when the agent finishes a response, executing verification-gate.sh. From tdwhere123/do-it.

tdwhere123/do-it

Agent

Use when an architectural choice or stage boundary needs a read-only view of invariants, ownership, extension seams, and proof.

tdwhere123/do-it

Agent

Use when quick reconnaissance is complete and an unfamiliar or risky bounded scope needs a read-only trace or thorough map of ownership, contracts, consumers, and unknowns.

tdwhere123/do-it

Agent

Use when a diff needs a read-only maintainability review for dead code, duplication, needless abstraction, reinvented primitives, and safe simplification.

tdwhere123/do-it

Agent

Use when documentation must be updated to accurately reflect verified repository behavior, tooling, installation, or operator workflows.

tdwhere123/do-it

Agent

Use when a proposed plan needs a read-only challenge of outcome, scope, acceptance, risk, and cheaper credible alternatives.

tdwhere123/do-it

Agent

Use when a feature or decision needs a read-only product lens on user goal, boundary, viable options, and tradeoffs.

tdwhere123/do-it

Agent

Use when a change or design needs a read-only adversarial review of trust boundaries, failures, state, persistence, concurrency, or replay.

tdwhere123/do-it

Agent

Use when a diff or delivered behavior needs a read-only correctness review for reachability, contract regressions, errors, and missing proof.

tdwhere123/do-it

Agent

Use when a delivered change needs a read-only check against the written task, acceptance criteria, explicit deferrals, and ownership boundaries.

tdwhere123/do-it

Agent

Use when a behavior change benefits from a narrow failing test before implementation and a test-only write scope is available.

tdwhere123/do-it

Skill Claude CodeCodex

Use when work changes or evaluates load-bearing authority, ownership, public or persisted contracts, dependency boundaries, migration/cutover, recovery, guards, or structural deletion.

tdwhere123/do-it

Skill Claude CodeCodex

Use when writing or designing code: name premise and blast radius, deepen modules at seams, TDD at agreed seams, diagnose before patching, and keep producer→consumer contracts honest.

tdwhere123/do-it

Skill Claude CodeCodex

Use when repo terms or invariants are drifting, or when user/docs/code naming disagrees and a canonical glossary is needed — .do-it/CONTEXT.md is the downstream source of truth for names, relationships, and facts.