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 handoff-prompt-stale-user-hint-newer-stategit 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/handoff-prompt-stale-user-hint-newer-state)<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/handoff-prompt-stale-user-hint-newer-state"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/handoff-prompt-stale-user-hint-newer-state/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/handoff-prompt-stale-user-hint-newer-state"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/handoff-prompt-stale-user-hint-newer-state.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 | $0.00340 | $0.02903 |
| Opus 5 | $0.00170 | $0.01452 |
| Sonnet 5 | $0.00068 | $0.00581 |
| Haiku 4.5 | $0.00034 | $0.00290 |
Grade A, and why
handoff-prompt-stale-user-hint-newer-state 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 12d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stale handoff prompt: user hints newer state landed since authoring
Problem
You're asked to execute a structured prompt (handoff, runbook, plan, ADR, implementation
spec) that was authored at time T0. The user's invocation includes a casual aside —
"but please be aware of #X, #Y, #Z" / "watch out for PR #N" / "FYI X landed". Between
T0 and execution, those artifacts were filed or merged and they materially change
what the prompt should do.
The default behavior is to execute the prompt verbatim and surface any divergence in a post-execution comment. That's wrong: the user is telling you the premise has changed and is asking you to re-evaluate scope before executing.
Failure mode: you ship the prompt's original plan, the newer state's implications get documented retroactively, and the user has to file a follow-up PR (or worse — a fix-up PR after auto-deploy) to reconcile.
Trigger conditions
Activate this skill when all of these hold:
-
The user's instruction has two parts: (a) "execute / run / implement [structured prompt file or runbook]" AND (b) an aside flagging GitHub issues, PRs, commits, or state-of-the-world that should be "aware of" / "factor in" / "watch out for" / "FYI." Phrasings include:
- "execute X, but be aware of #N"
- "run the prompt — watch out for PR #M"
- "implement this, factoring in #issue"
- "but FYI #N was filed since"
- "remember #X is open now"
-
Before any code changes, a quick check (
gh issue view,gh pr view,git log) shows at least one hinted artifact was filed/merged AFTER the prompt's authoring timestamp (Date:line, frontmatter, git mtime, or first commit on the prompt's feature branch). -
The artifact's content is non-trivial — a P1+ issue, a merged PR, a probe verdict, a panel review request_changes. (If the hint is just "remember the deploy schedule is Friday" — that's calendar context, not a scope change. Don't fire this skill.)
Solution
Step 1: Pause before the first scope-affecting action.
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.
- 12d ago First seen · 216 lines · 340 tokens per session scan A 0649f08d8b80
handoff-prompt-stale-user-hint-newer-state is a skill published in the GitHub repository wan-huiyan/agent-traffic-control (3 stars, last pushed yesterday), licensed MIT. It adds 340 tokens to every session and 2,903 once invoked, about $0.0017 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
codex-coplan
Bring in an external model (Codex) to co-develop a plan — both models draft independently, align on disagreements, and merge into one plan. Load this only when the user explicitly names Codex (e.g. "let's discuss this with Codex," "what does Codex think about this approach") — don't auto-trigger just because a plan…
codex-orchestrator
Delegate execution tasks to Codex (Claude plans and reviews). Load this only when the user names Codex explicitly — no matter how big the task is, if the user hasn't mentioned Codex, do it yourself.
good-bad-ugly
Use when the user asks to "orchestrate", "conduct", invoke "good bad ugly" / "gbu", or tackle a large multi-part coding task (audits, refactor sweeps, multi-feature sessions, "clean this up and fix everything") — anything too big for one linear pass. Runs the tiered orchestration workflow: The Good (brain) plans and…
orchestrate
Use only when the user explicitly types /orchestrate:orchestrate to decompose a large task, spawn a tree of parallel worker/subplanner/verifier subagents, and collect structured handoffs. Do not invoke autonomously.
api-testing
HTTP API testing for TypeScript (Supertest) and Python (httpx, pytest). Test REST APIs, GraphQL, request/response validation, authentication, and error handling.
bun-test-coverage
Use for test coverage with Bun, --coverage flag, lcov reports, thresholds, and CI integration.