wan-huiyan

99 mods across 5 repositories, 41 stars between them.

agent-review-panel

01

wan-huiyan/agent-review-panel

Plugin Claude Code

Claude Code plugin marketplace for the roundtable plugin — multi-agent adversarial review panel that bundles two skills: agent-review-panel (panel-based code/plan review) and plan-review-integrator (apply review findings back into implementation plans).

35 20d ago A tokens not measured original MIT

roundtable

02

wan-huiyan/agent-review-panel

Plugin Claude Code

Multi-agent adversarial review panel — 4-6 AI reviewers debate your code/plans, then a judge delivers a structured verdict with epistemic labels. Bundles plan-review-integrator for applying review findings back into implementation plans.

35 20d ago A tokens not measured original MIT

agent-review-panel

03

wan-huiyan/agent-review-panel

Skill Claude CodeCodex

Orchestrate a multi-agent adversarial review panel: subagents with different perspectives independently review, debate and discuss, reach or fail consensus, then a supreme judge renders the verdict. Trigger on "review panel", "multi-agent review", "adversarial review", "panel review", "have agents debate this", "get…

35 20d ago A 328 tokens original MIT

wan-huiyan/agent-review-panel

Skill Claude CodeCodex

Integrate structured review panel findings into an implementation plan document. Takes output from agent-review-panel (or any structured review with severity-rated findings) and cross-references each finding against the plan, classifies it into an action category, applies concrete edits, and produces a traceability…

35 20d ago A 197 tokens original MIT

wan-huiyan/agent-traffic-control

Plugin Claude Code

Coordination toolkit for parallel Claude Code sessions sharing one repo — issue-pickup claim protocol (assignee + wip label), worktree & session-isolation pitfalls, parallel-PR conflict recovery, subagent-integrity edge cases, and squash/merge mechanics for parallel-PR workflows.

3 14d ago A tokens not measured original MIT

wan-huiyan/agent-traffic-control

Plugin Claude Code

Coordination toolkit for parallel Claude Code sessions sharing one repo — issue-pickup claim protocol (assignee + wip label), worktree & session-isolation pitfalls, parallel-PR conflict recovery, subagent-integrity edge cases, and squash/merge mechanics for parallel-PR workflows. Plus resume-gate, an opt-in hook that…

3 14d ago A tokens not measured original MIT

wan-huiyan/agent-traffic-control

Skill Claude CodeCodex

Fix for git checkout failing with fatal: ' ' is already used by worktree at '.../autodocs- ' (or a subagent reviewing a PR reports a path like .../worktrees/autodocs- /...). Use when: (1) right after a commit whose hook printed [post-commit] Python files changed — running doc update in background..., a later branch…

3 14d ago A 251 tokens original MIT

wan-huiyan/agent-traffic-control

Skill Claude CodeCodex

In a repo with an ASYNC/background post-commit hook (one that fires after a commit and creates its OWN follow-up commit — [auto-docs] …, a docs/site regen, a changelog/checkbox tick), the hook's commit can land LOCAL-ONLY after your git push already captured just your work commit, so it is never in the PR and gets…

3 14d ago A 409 tokens original MIT

wan-huiyan/agent-traffic-control

Skill Claude CodeCodex

When generating LONG Chinese/Japanese/Korean (CJK) STRUCTURED output (a big JSON report, a multi-section document) from an LLM chat API, the response truncates mid-JSON and your parser throws "no parseable JSON" / "Expecting ',' delimiter" / JSONDecodeError — even though the SAME prompt in English worked. Root cause…

3 14d ago A 227 tokens original MIT

wan-huiyan/agent-traffic-control

Skill Claude CodeCodex

When a code-review subagent (voltagent-qa-sec, opus-tier reviewer, code-reviewer, etc.) reports a HIGH or BLOCKING severity finding, verify any SPECIFIC EVIDENCE the reviewer cites (line numbers, call counts, exact function/symbol names, file paths beyond the obvious diff) BEFORE treating the severity as actionable.…

3 14d ago A 428 tokens original MIT

wan-huiyan/agent-traffic-control

Skill Claude CodeCodex

Code-review subagents are frequently provisioned WITHOUT a Bash tool, so they cannot run gh pr diff, git diff, or git checkout — and when you prompt them to "review PR #N, fetch the diff with gh pr diff" they return a BLOCKED report (no review performed), not findings. Use when: (1) dispatching…

3 14d ago A 214 tokens original MIT

wan-huiyan/agent-traffic-control

Skill Claude CodeCodex

A second Claude Code session (or agent/person) sharing the same working directory runs git checkout/git switch, flipping the branch for the whole working tree underneath your session and clobbering your uncommitted work. Use when: (1) a file you just edited has silently reverted — often with a "file was modified…

3 14d ago A 214 tokens original MIT

wan-huiyan/agent-traffic-control

Skill Claude CodeCodex

Recover gracefully when an Anthropic credit/billing failure stalls multiple in-flight parallel subagents mid-orchestration, then later resolves. Use when: (1) you've dispatched 2+ parallel subagents (Task tool with runinbackground: true) and a credit/billing issue, MCP outage, or other transient harness failure has…

3 14d ago A 303 tokens original MIT

wan-huiyan/agent-traffic-control

Skill Claude CodeCodex

Pass a shared file between two parallel sessions in different worktrees or branches, without merging to main first — a design spec, docs, a handoff prompt, a mockup. git checkout -- stages it. Use when a session says "the file doesn't exist". Not co editing.

3 14d ago A 79 tokens original MIT

wan-huiyan/agent-traffic-control

Skill Claude CodeCodex

Dispatching a review or verification agent with live database, gcloud, psql or bash access: give it a tool call and time budget, plus the probes NOT to re-run. Also when it gives API Error: The socket connection was closed unexpectedly, or has run 30 minutes. Not its sources.

3 14d ago A 77 tokens original MIT

wan-huiyan/agent-traffic-control

Skill Claude CodeCodex

Diagnose "I deployed a new Cloud Run / Docker image but a bunch of recently merged fixes regressed in production." Use when: (1) the deploy script does gcloud builds submit ... "${SCRIPTDIR}" or docker build (build context = local filesystem, NOT a git ref), (2) the user has many git worktrees / multiple checkouts of…

3 14d ago A 405 tokens original MIT

wan-huiyan/agent-traffic-control

Skill Claude CodeCodex

Catch the failure where a subagent dispatched ONLY to DECIDE/DESIGN (a judge, a design-panel synthesizer, a "pick the mechanism" agent) instead EXECUTES the plan — and, having full Bash/gcloud/bq, provisions LIVE infrastructure (creates a BQ dataset/table, a DTS scheduled query, a log metric, a paging alert policy)…

3 14d ago A 341 tokens original MIT

wan-huiyan/agent-traffic-control

Skill Claude CodeCodex

A verification/review/audit subagent YOU dispatched (Workflow agents, Explore, general-purpose, code-reviewer — anything with Bash) runs a file-level git checkout / git restore / git stash to compare your work against HEAD, and silently REVERTS your uncommitted working-tree edit in the shared worktree. The agent then…

3 14d ago A 409 tokens original MIT

wan-huiyan/agent-traffic-control

Skill Claude CodeCodex

Catch the bug class where a "docs follow-up" PR silently ships the parent feature's code under a docs(sN): title because the docs branch was created from the current working branch (a feature branch), not from origin/main. Use when: (1) you just opened a PR titled docs(...) or chore(...) after wrapping up a feature…

3 14d ago A 454 tokens original MIT

wan-huiyan/agent-traffic-control

Skill Claude CodeCodex

A prompt/brief/runbook file and the index that lists it are SHARED STATE between parallel sessions, so finishing the work is only half of finishing: the session that executes a brief must retire it on BOTH surfaces, and the session that writes one must register it, or a sibling redoes work that already merged or never…

3 14d ago A 382 tokens original MIT

wan-huiyan/agent-traffic-control

Skill Claude CodeCodex

Use when a Workflow (or background Agent) synthesis step returns a LARGE markdown deliverable inside a structured-output (schema) field — e.g. a nextpromptmarkdown, a full report, a generated doc — and you need to persist it to a file. The completion notification TRUNCATES the result and shows the field JSON-escaped…

3 14d ago A 185 tokens original MIT

wan-huiyan/agent-traffic-control

Skill Claude CodeCodex

Writing the prompt for a verifier that will "fact check" or "verify" a document or report against sources: hand it complete originals, never your own partial dump. And a verdict back that calls a claim "unsupported" or "fabricated" — check the gap is not in a source you trimmed.

3 14d ago A 75 tokens original MIT

wan-huiyan/agent-traffic-control

Skill Claude CodeCodex

Diagnose "I edited the template / view / CSS but Flask debug-mode keeps serving the old version" when running a local dev server (Flask, Django runserver, Rails server, etc.) from one git worktree while editing files in a sibling worktree of the same repo. Use when: (1) you have multiple git worktree checkouts of the…

3 14d ago A 345 tokens original MIT