wan-huiyan/agent-traffic-control
Skill Claude CodeCodex
Diagnose "I merged my PR + CI is green but the live service still doesn't show my changes." Use when: (1) a code-bearing PR has been squash-merged into main with all required status checks passing, (2) the user reports the change is still missing from the deployed environment minutes-to-hours later, (3) the repo has a…
wan-huiyan/agent-traffic-control
Skill Claude CodeCodex
Diagnose and fix silent compression of MANDATORY phases in multi-agent orchestrator skills (review panels, debate workflows, multi-reviewer pipelines). Use when: (1) a skill spec lists 10+ phases including parallel reviewer dispatch but the actual run "compresses Phase 4 (reflection) / Phase 5 (debate) / Phase 7…
wan-huiyan/agent-traffic-control
Skill Claude CodeCodex
Fix silent subagent failures in late phases of multi-phase Claude Code skills. Use when: (1) a skill has 10+ phases and the last phase's subagent silently fails to launch, (2) Phase N produces output that Phase N+1 needs but the orchestrator's context is near capacity, (3) the orchestrator injects large data payloads…
wan-huiyan/agent-traffic-control
Skill Claude CodeCodex
When a user opens a file:// URL bookmark to a file in a repo with multiple git worktrees, the browser shows whatever the targeted worktree's branch contains — NOT main, NOT the latest merge. Use when: (1) user reports "I don't see my change" or "the fix isn't there" right after a PR was merged, (2) you've confirmed…
wan-huiyan/agent-traffic-control
Skill Claude CodeCodex
When a large Workflow/Agent fan-out (dozens of parallel subagents on Opus) mass-fails with "Server is temporarily limiting requests (not your usage limit)" / HTTP 429 — most agents dying, a few that finished before the burst surviving — recover by re-running the SAME fan-out on Sonnet and throttled into sequential…
wan-huiyan/agent-traffic-control
Skill Claude CodeCodex
A dispatched parallel implementation subagent can die mid-stream and leave ZERO durable output while the harness still reports the task "completed". Use when: (1) you fanned out 2+ foreground impl agents (Agent/Task tool) to edit code in one repo, (2) one returns API Error: Response stalled mid-stream / an empty or…
wan-huiyan/agent-traffic-control
Skill Claude CodeCodex
Before applying a handoff prompt's tiebreaker default ("merge the first-mover", "the clean-against-main one", "the one with reviewer APPROVE") to pick a winner between two parallel PRs that implemented the SAME scope, run gh pr diff on BOTH and audit for substantive deltas. Use when: (1) a session prompt or handoff…
wan-huiyan/agent-traffic-control
Skill Claude CodeCodex
Diagnose silent semantic duplication after two parallel PRs ship. Use when: (1) one PR (the mover) relocates a section/component/block from template X to template Y (X loses it, Y gains it), (2) a sibling PR (the forker), authored against pre-mover main, creates / promotes / copies template Z from the OLD version of X…
wan-huiyan/agent-traffic-control
Skill Claude CodeCodex
Edit a shared deliverable while another live session or a colleague's agent is editing the same file right now — "don't delete each other's work", "only write when the other one is finished". When the file is built from many per item sources by an assembler (sections into one HTML, slides, reports): source mtime shows…
wan-huiyan/agent-traffic-control
Skill Claude CodeCodex
Large parallel subagent fan-outs (dispatching many Agent/Task subagents at once to each extract/transform a chunk and WRITE a file) hit a server-side rate limit, AND the agent RETURN STATUS lies about what got produced. Use when: (1) dispatching more than 5-6 concurrent subagents and seeing "Server is temporarily…
wan-huiyan/agent-traffic-control
Skill Claude CodeCodex
A pull request that was clean when you opened it now says on GitHub "This branch has conflicts that must be resolved", because others landed on main over the days it sat open. Use when gh pr view N --json mergeable,mergeStateStatus returns CONFLICTING and DIRTY, when your branch carries commits you do not recognise…
wan-huiyan/agent-traffic-control
Skill Claude CodeCodex
Diagnose and recover follow-up commits that were pushed to an open PR's branch but never reached main because the user squash-merged the PR between pushes. Use when: (1) you pushed commit 1, opened a PR, then iteratively pushed commits 2, 3, ... in response to user feedback, (2) you go to merge / verify and find the…
wan-huiyan/agent-traffic-control
Skill Claude CodeCodex
Trap: merging a PR whose branch carries an OLD TREE silently DELETES (reverts) files that landed on main after that tree was built — with NO merge conflict to warn you, because a deletion your own commit records is not a conflict. Use when: (1) about to gh pr create or squash-merge from a long-lived / earlier-branched…
wan-huiyan/agent-traffic-control
Skill Claude CodeCodex
Diagnose and recover from accidentally overwriting another session's open PR when git push -u origin in a long-lived worktree silently replaces the remote branch ref. Use when ANY of the following appears: (1) you ran git checkout -b origin/main and git push -u and git reported [new branch] even though the branch…
wan-huiyan/agent-traffic-control
Skill Claude CodeCodex
Before writing detailed pull request plans against a codebase you have not audited, triage it by bucket so sizes rest on findings rather than assumptions.
wan-huiyan/agent-traffic-control
Skill Claude CodeCodex
Telling an agent in its prompt it has "your own isolated worktree" creates nothing — isolation is the dispatch call's isolation: "worktree" parameter. Before fanning out agents that will commit, read the CALL back and make each prove where it landed. Prevention, not cleanup.
wan-huiyan/claude-ecosystem-hygiene
Plugin Claude Code
Nine complementary skills for auditing, measuring, and maintaining Claude Code ecosystem health and project test quality. Audit → measure (Claude stack + project tests) → clean → stay consistent: identify HOT vs DORMANT artifacts, measure whether the HOT ones actually improve outcomes, measure whether your project's…
wan-huiyan/claude-ecosystem-hygiene
Plugin Claude Code
Counterfactual A/B + layered-ablation harness for Claude Code setup. Measures whether your /.claude/ stack (skills, lessons, axioms, memory) plus in-repo discipline (docs/runbooks, decisions, findings) actually helps on real tasks. Binary A/B (setup-ON vs setup-OFF) and layered ablation (strip one layer at a time, ran.
wan-huiyan/claude-ecosystem-hygiene
Skill Claude CodeCodex
Run a counterfactual A/B harness on Claude Code to measure whether the user's /.claude setup (memories, lessons, axioms, skills, hooks, plugins) actually helps on real tasks vs. a blank-canvas env. Use when: (1) User wants to "prove my setup works" or "quantify setup impact" to colleagues; (2) User asks "is my setup…
wan-huiyan/claude-ecosystem-hygiene
Plugin Claude Code
Wire up CI validation and automatic release-cutting for a Claude Code plugin or marketplace repo (one with a .claude-plugin/marketplace.json and plugins/). Adds two GitHub Actions — a structure validator on every PR/push, and a release-on-version-bump job that cuts a GitHub Release whenever VERSION changes — plus the.
wan-huiyan/claude-ecosystem-hygiene
Skill Claude CodeCodex
Wire up CI validation and automatic release-cutting for a Claude Code plugin or marketplace repo (a repo with a .claude-plugin/marketplace.json and plugins/). Adds two GitHub Actions — a structure validator that runs on every PR/push, and a release-on-version-bump job that cuts a GitHub Release whenever a VERSION file…
wan-huiyan/claude-ecosystem-hygiene
Plugin Claude Code
Measure, trim, and report the token cost of a runaway Claude Code skills/agents catalog (injected every turn + into every subagent) — verified per-project skillOverrides + global disable-model-invocation levers, an interactive HTML recap, and the durable root-cause fix (curate episodic lessons out of the always-on…
wan-huiyan/claude-ecosystem-hygiene
Skill Claude CodeCodex
Use when an agent harness's skills/tools catalog has grown large (hundreds+, e.g. an auto-skill-minting loop) and is taxing context: the name+description listing is injected every turn AND into every subagent, so cost multiplies on fan-out and small-context agents can overflow ("Prompt is too long" at 0 tokens). Also…
wan-huiyan/claude-ecosystem-hygiene
Plugin Claude Code
Detect stale normative guidance in project docs/ after the user adds a new "don't X / avoid Y" rule to /.claude/lessons.md, /.claude/axioms.md, or a per-project feedback.md entry. Event-driven PostToolUse hook + weekly cron audit. Lists file:line candidate stale claims — never auto-edits. Conservative guardrails: e.