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 executed-prompt-not-retired-sibling-redoes-itgit 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/executed-prompt-not-retired-sibling-redoes-it)<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/executed-prompt-not-retired-sibling-redoes-it"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/executed-prompt-not-retired-sibling-redoes-it/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/executed-prompt-not-retired-sibling-redoes-it"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/executed-prompt-not-retired-sibling-redoes-it.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 | $0.00382 | $0.02372 |
| Opus 5 | $0.00191 | $0.01186 |
| Sonnet 5 | $0.00076 | $0.00474 |
| Haiku 4.5 | $0.00038 | $0.00237 |
Grade A, and why
executed-prompt-not-retired-sibling-redoes-it 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
An executed prompt nobody retired: the next session redoes merged work
Problem
A repo keeps session briefs in docs/handoffs/ with an index, next_session_prompt.md, whose
table says which are live. Sessions run in parallel and pick their work off that table.
Session A executes 2026-08-05-registered-scope-drift.md in full: the analysis lands, a ruling
is committed, the issue is closed, the PR merges. Session A writes an excellent handoff about
what it found.
It does not touch the brief it executed, or the row that pointed at it.
An hour later the index still reads:
| 2026-08-05-registered-scope-drift.md | ... | live, unclaimed — **TAKE THIS ONE** |
and the brief itself still opens "Nothing here is blocked and nothing needs the owner to start." A fresh session, told only "read the index and take the top row", starts re-deriving a result that merged an hour ago.
The same repo hit the identical shape twice in one day: a second stream's brief said "task 1: classify the marks", the marks had been classified that morning, and the PR that caught it is titled "the prompt would have commissioned a rival tally against the committed one" — the danger is not just wasted time, it is a second, divergent artifact for a question already answered.
And the mirror-image half: three workstream-*.md prompts sat in the directory for a day
with no row in the index at all, so a session reading only the index could not see them —
including the one stream that could have run to completion that day.
Context / Trigger Conditions
Any of:
- You are about to execute a brief selected from an index, and the index calls it live / unclaimed / next / "take this one".
- You have just finished executing a brief and are writing the wrap-up.
- You just authored a prompt for a future session.
- Two or more index rows carry "next" — which is the same as none carrying it.
- A prose row count sits beside a table other sessions append to.
Environmental smell: parallel sessions, a solo maintainer who self-merges, and a hand-edited index. Nothing in CI reads prose, so no gate catches any of this.
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 · 194 lines · 382 tokens per session scan A 5838098dcd11
executed-prompt-not-retired-sibling-redoes-it is a skill published in the GitHub repository wan-huiyan/agent-traffic-control (3 stars, last pushed today), licensed MIT. It adds 382 tokens to every session and 2,372 once invoked, about $0.0019 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.