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 batch-member-cites-a-path-only-a-non-member-addsgit 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/batch-member-cites-a-path-only-a-non-member-adds)<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/batch-member-cites-a-path-only-a-non-member-adds"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/batch-member-cites-a-path-only-a-non-member-adds/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/batch-member-cites-a-path-only-a-non-member-adds"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/batch-member-cites-a-path-only-a-non-member-adds.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 | $0.00053 | $0.04218 |
| Opus 5.5 | $0.00021 | $0.01687 |
| Sonnet 5.5 | $0.00011 | $0.00844 |
| Haiku 4.5 | $0.00005 | $0.00422 |
Grade A, and why
batch-member-cites-a-path-only-a-non-member-adds 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 14d 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 — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A Batch Member Can Cite a Path Only a Non-Member Adds
Problem
Batch assembly asks one question about files: do two members touch the same file? That decides membership, because two members editing one file collide. It is the right question and it is asked.
There is a second question, and nothing asks it: does a file a member adds or changes NAME a path that only a pull request OUTSIDE the batch adds?
The two are not the same shape. Overlap is symmetric and it is about editing. This one is
directional and it is about referring. A member can cite a path no member creates, and the
citation is just text — inside a # comment, a docstring, a markdown link, a JSON string in a
hand-edited data file. Nothing in a normal gate resolves it:
- the compiler and the interpreter never read comments or docstrings;
- test suites assert behaviour, not that a cited path exists;
- a link checker, if there is one, usually runs on docs and not on source comments;
- a tracker validator checks enums and required fields, not that a
hrefresolves.
So the batch merges green, and the target branch now has a sentence pointing at a file it does not have. The reader who follows it finds nothing, and cannot tell whether the path is wrong, the file was deleted, or it never arrived.
The failure is quiet in both directions. If the sibling lands a day later, the citation silently becomes true and nobody learns anything. If the sibling is abandoned, the dangling path sits there indefinitely, and the figure it was supposed to support has no source.
Context / Trigger Conditions
Run this check when all of these hold:
- you are assembling or about to flip a batch, roll-up, merge train, or any set of pull requests intended to land together;
- at least one member's diff adds or changes prose — comments, docstrings, markdown, a tracker or metadata file — as opposed to only code and tests;
- there exist open pull requests that are NOT in the batch. (If every open pull request is in the batch, a cited path either exists or was never coming, and the check collapses to a plain existence test.)
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.
- 14d ago First seen · 327 lines · 53 tokens per session scan A 0e020e1f76bb
batch-member-cites-a-path-only-a-non-member-adds is a skill published in the GitHub repository wan-huiyan/agent-traffic-control (3 stars, last pushed 15d ago), licensed MIT. It adds 53 tokens to every session and 4,218 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-23.
Other skills, from other repositories
signing-preflight
Before the first commit of a session, check that commit signing will work — the key is loaded and unlocked — and ask the operator to unlock it once, up front, instead of discovering it after a hundred unsigned commits. Never disables signing silently, never re-signs history without asking. Use at the start of…
review
Review a change with what this repository knows about it — who depends on the file, which tests cover it, what broke here before, and what the repo has written down. Use before approving a diff, opening a PR, or when asked to review.
misuzu
Respond to PR review comments semi-automatically. Fetches all review threads and comments, splits them into logical units, fixes and commits one unit at a time, then replies and resolves review threads. Use when the user wants to address PR review feedback or respond to review comments.
pr-authoring
Playbook for deployment-aware pull requests — the 11-section format that turns a PR into a reviewable contract; why, decision requested, change map, review order, evidence, verification, risk, rollback. Used for the Define→build handoff and any PR a great-pm-driven project opens.
pr-review
Playbook for reviewing pull requests — verdict format, verification-not-trust, severity-ranked findings with concrete fixes, risk acceptance on the record. The reviewer-side counterpart of pr-authoring.
pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.