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 parallel-pr-template-fork-duplicates-moved-sectiongit 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/parallel-pr-template-fork-duplicates-moved-section)<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/parallel-pr-template-fork-duplicates-moved-section"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/parallel-pr-template-fork-duplicates-moved-section/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/parallel-pr-template-fork-duplicates-moved-section"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/parallel-pr-template-fork-duplicates-moved-section.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 | $0.00308 | $0.03244 |
| Opus 5 | $0.00154 | $0.01622 |
| Sonnet 5 | $0.00062 | $0.00649 |
| Haiku 4.5 | $0.00031 | $0.00324 |
Grade A, and why
parallel-pr-template-fork-duplicates-moved-section 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 10d 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel-PR Template Fork Duplicates Moved Section
Problem
Two PRs ship within hours of each other. Neither shows a textual merge conflict. Both pass tests. Both deploy cleanly. After deploy, a user reports "this section is appearing in two places now — that's wrong, right?"
The mechanism is structural, not textual:
- PR #A (mover): relocates a
<section>...</section>from templateX.htmlto templateY.html.Xloses the block;Ygains it. - PR #B (forker): promotes / copies / forks
X.htmlinto a new templateZ.html(e.g., the route is moving up in the IA, or the page is being split). The fork is literal —Z.htmlwas authored as a near-copy ofX.htmlas it existed before the mover landed. - The two PRs touch different files on disk. Squash-merge is "clean" by
git's textual measure:
Xlost a block (mover),Ygained it (mover),Zwas added (forker). No 3-way merge conflict. - Reality:
Zwas forked from a snapshot ofXthat still contained the section. So after both ship, the block lives in BOTHYandZ.
The user sees the duplication immediately. Code review on each PR in isolation wouldn't have caught it — each diff was correct against its own base.
Trigger conditions
ALL of these are typically true:
- Two PRs merged to main within a short window (hours / a day), authored independently.
- One PR's diff includes lines that look like "move section from X to Y" — classic markers: deletion in one template, equivalent insertion in another, plus a comment saying "moved per IA brief §N" or similar.
- The other PR's diff includes "create new template Z" or "rename X → Z"
where the
+lines for Z look very similar to (or are a literal copy of) the pre-mover version of X. - Neither PR's branch was rebased onto the other after both were opened.
- User-visible symptom: rendered HTML on two different routes contains the
same heading / chart / SVG / id (e.g.,
<h2>Feature Snapshot</h2>orid="feature-radar-chart"appears on/route-yAND/route-z). - Tests still pass because each route's tests were authored to assert on their own template; cross-route uniqueness wasn't part of the contract.
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.
- 10d ago First seen · 289 lines · 308 tokens per session scan A 2d29b364626c
parallel-pr-template-fork-duplicates-moved-section is a skill published in the GitHub repository wan-huiyan/agent-traffic-control (3 stars, last pushed 5d ago), licensed MIT. It adds 308 tokens to every session and 3,244 once invoked, about $0.0015 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
ql-housekeep
Detect repo-hygiene issues that accumulate during long-running autonomous development (merge-conflict markers, orphan worktrees, CPC-variant duplicates, stale branches, version-manifest drift). Detection-only by default — reports findings, never deletes or modifies without explicit user confirmation.
nazgul:doctor
Run the Nazgul read-only preflight diagnostic — checks jq/gh presence and auth, git-hooks drift, cache-vs-repo plugin version, the bash-vs-zsh hazard, the NAZGULDIR footgun, config-schema staleness, either install mode's .gitignore Nazgul-block drift (stamp and flush-left region), cross-session messaging and Remote…
hotfix
Emergency fix workflow that bypasses normal sprint processes with a full audit trail. Creates hotfix branch, tracks approvals, and ensures the fix is backported correctly.
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.
cloudflare-workers-observability
Cloudflare Workers observability with logging, Analytics Engine, Tail Workers, metrics, and alerting. Use for monitoring, debugging, tracing, or encountering log parsing, metric aggregation, alert configuration errors.
cloudflare-workers-dev-experience
Cloudflare Workers local development with Wrangler, Miniflare, hot reload, debugging. Use for project setup, wrangler.jsonc configuration, or encountering local dev, HMR, binding simulation errors.