WangChangxin0809/repo-agent-harness
Plugin Claude Code
Plugins by WangChangxin0809. Currently one: a repository-side harness for coding agents.
WangChangxin0809/repo-agent-harness
Plugin Claude Code
Plugins by WangChangxin0809. Currently one: a repository-side harness for coding agents.
WangChangxin0809/repo-agent-harness
Plugin Claude Code
Lay the foundation that makes a repository teach coding agents how to work in it: delivery moments wired to hooks, a layered docs truth source, CI gates plus tool-call guards, a rebuildable repo graph, and a consolidation pass. Bootstraps once, then the repo stands on its own.
WangChangxin0809/repo-agent-harness
Hook Claude Code
Runs before the agent uses a tool for Bash, Bash, Write, Edit and MultiEdit tool calls, executing dispatch.py and before_write.py via python3 (2 commands). From WangChangxin0809/repo-agent-harness.
WangChangxin0809/repo-agent-harness
Hook Claude Code
Runs when a session starts, executing session_brief.py via python3. From WangChangxin0809/repo-agent-harness.
WangChangxin0809/repo-agent-harness
Hook Claude Code
Runs when the agent finishes a response, executing on_stop.py via python3. From WangChangxin0809/repo-agent-harness.
WangChangxin0809/repo-agent-harness
Hook Claude Code
Runs after instructions files are loaded for path_glob_match tool calls, executing before_write.py via python3. From WangChangxin0809/repo-agent-harness.
WangChangxin0809/repo-agent-harness
Settings file Claude Code
Agent settings declaring 4 hook events (PreToolUse, SessionStart, Stop, InstructionsLoaded).
WangChangxin0809/repo-agent-harness
Instructions file
Claude Code instructions for WangChangxin0809/repo-agent-harness, covering repo-agent-harness, three identities, one tree, hard rules, commands and where to look.
WangChangxin0809/repo-agent-harness
Agent
Answers "where does X happen, and what would break if I changed it" for a repository, by querying the repo graph and reading what it points at. Use when the answer needs more than three files read — it returns a conclusion with citations instead of file dumps.
WangChangxin0809/repo-agent-harness
Skill Claude CodeCodex
Lay the foundation that makes a repository teach coding agents how to work in it — CLAUDE.md and its subtree files, .claude/ hook wiring, a layered docs/ truth source, scripts/ gates and guards, and a decision record explaining the shape. Use this whenever someone says the agent keeps repeating a mistake, that rules…
WangChangxin0809/repo-agent-harness
Skill Claude CodeCodex
Merge an accumulated pile of agent notes, memories, or scratch documents into repository knowledge — freezing the input, synthesizing into a separate output, diffing, and routing each surviving entry to a doc, a guard, a subtree CLAUDE.md, or the small remainder that really is user-scoped. Also covers pruning docs and…
WangChangxin0809/repo-agent-harness
Skill Claude CodeCodex
Give a repository a code-and-docs graph an agent can query — tree-sitter symbols, import and call edges, doc-to-code edges, ranked by personalized PageRank from whatever the current task touches. Use this when an agent cannot find the relevant code in a large repo, when grep returns hundreds of hits or none, when…
WangChangxin0809/repo-agent-harness
Skill Claude CodeCodex
Build the machinery that enforces a convention instead of documenting it — PreToolUse guards that block an action before it runs, CI gates that judge the worktree, selftests that prove a check can turn red, and structural tests that enforce layering. Use this whenever a rule keeps getting violated despite being…
WangChangxin0809/repo-agent-harness
Skill Claude CodeCodex
Write or restructure documentation that agents and people actually read — choosing which of the four directories it belongs in (how-to, reference, decisions, exec-plans), knowing what belongs in a failure message instead of a file, and keeping the routing table honest. Use this whenever writing a doc, a runbook, a…
WangChangxin0809/repo-agent-harness
Skill Claude CodeCodex
Write the repository's public face — README.md, CONTRIBUTING.md, and the GitHub community health files (SECURITY, CODEOFCONDUCT, LICENSE, issue and pull request templates). Use this when creating or rewriting any of those, when deciding whether a sentence belongs in the README or in CONTRIBUTING, when GitHub's…