Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add wan-huiyan/agent-traffic-control --skill gh-issue-claim-coordinationgit clone --depth 1 https://github.com/wan-huiyan/agent-traffic-controlWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/gh-issue-claim-coordination)<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/gh-issue-claim-coordination"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/gh-issue-claim-coordination/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/gh-issue-claim-coordination"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/gh-issue-claim-coordination.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00077 | $0.03127 |
| Opus 5 | $0.00039 | $0.01563 |
| Sonnet 5 | $0.00015 | $0.00625 |
| Haiku 4.5 | $0.00008 | $0.00313 |
Grade A, and why
gh-issue-claim-coordination scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub issue claim coordination (assignee + label)
When multiple Claude Code sessions (or human + agent) work the same repo in parallel, two sessions can independently pick up the same issue, do parallel implementations, and collide at PR time — burning hours of duplicated work and forcing one branch to be rebased or abandoned.
Default agent behaviour is silent. An agent dispatched to "work on the bug-tagged issues" does not automatically check whether another session is already on issue #N. There's no built-in coordination unless this skill (or equivalent) runs at pickup.
This skill installs a 60-second protocol — preflight check, atomic claim, stale-claim sweep, release on completion — using two GitHub-native primitives so the claim is visible everywhere (issue list UI, gh issue list, dashboards, sibling sessions).
Why both assignee AND a wip label?
They cost ~0 to set together and cover different failure modes:
assigneesis GitHub's canonical "who's on this" primitive.gh issue list --assignee ""cleanly enumerates unclaimed work; agents tend to surface assignees in their own context without prompting.- A
wiplabel is far more visible in the GitHub issue list UI (a coloured chip next to the title) and lets you find every active claim with one query:gh issue list --label wip. It also survives the case where someone reassigns the issue without thinking about coordination.
Belt and suspenders. If the assignee gets dropped on a bulk edit, the label still flags it; if the label gets dropped, the assignee still says it.
Pickup protocol
Step 0: Ensure the wip label exists (idempotent — runs every time)
Don't carry "did I do the setup yet?" state. The label create is cheap and noisy on success only the first time; on subsequent runs it just exits non-zero with "already exists", which || true swallows. Bake it into every pickup so a fresh repo or a teammate's repo just works.
gh label create wip \
--description "Claimed by an active session — do not start parallel work" \
--color FBCA04 \
|| true
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago Changed · +45 lines 3a98a64b1d45
- 12d ago First seen · 168 lines · 77 tokens per session scan A 81085e68e320
gh-issue-claim-coordination is a skill published in the GitHub repository wan-huiyan/agent-traffic-control (3 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 3,127 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
cloudflare-workers-ci-cd
Complete CI/CD guide for Cloudflare Workers using GitHub Actions and GitLab CI. Use for automated testing, deployment pipelines, preview environments, secrets management, or encountering deployment failures, workflow errors, environment configuration issues.
claude-code-bash-patterns
Claude Code Bash tool patterns with hooks, automation, git workflows. Use for PreToolUse hooks, command chaining, CLI orchestration, custom commands, or encountering bash permissions, command failures, security guards, hook configurations.
bump-sdk-version
Bump the FutureSearch SDK version across all files. Use when releasing a new SDK version, updating version numbers, or the user says bump version, release, version bump.
pr-check
PR review compliance: fetch review comments from an open PR, categorize as resolved/unresolved/dismissed, critically evaluate fixable items, implement approved fixes, and reply inline. Pass --unattended to halt on human-judgment items (emitted as Pending-Human) instead of prompting via AskUserQuestion.
babysit
PR babysitter: monitors CI status, auto-rebases when behind, auto-fixes CI where possible, delegates review comment handling to dlc:pr-check, and re-requests review after fixes. Designed for /loop usage with Remote Control.
git-ops
Git hygiene: clean up merged branches, prune stale remotes, and verify repository state.