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 pr-plan-bucket-triage-before-sizinggit 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/pr-plan-bucket-triage-before-sizing)<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/pr-plan-bucket-triage-before-sizing"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/pr-plan-bucket-triage-before-sizing/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/pr-plan-bucket-triage-before-sizing"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/pr-plan-bucket-triage-before-sizing.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 | $0.00040 | $0.03562 |
| Opus 5 | $0.00020 | $0.01781 |
| Sonnet 5 | $0.00008 | $0.00712 |
| Haiku 4.5 | $0.00004 | $0.00356 |
Grade A, and why
pr-plan-bucket-triage-before-sizing 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 11d 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 — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase 0 Bucket Triage Before Writing PR Plans
Problem
superpowers:writing-plans produces detailed task-by-task plans with exact
file paths, LOC estimates, and TDD steps. That's the right output when you
know the codebase state — but a common failure mode is writing those
plans on assumptions about: which routes already exist, whether a colleague's
in-flight module is a stub or substantial, what storage convention links
results to runs, whether a "known defect" is still real or was quietly fixed.
You burn cycles writing detailed plans, the engineer starts implementing,
and within the first hour they discover the plan was sized against a
codebase that doesn't exist. The fix is always re-plan with the new
evidence — meaning the original plan was waste.
The cost of writing plans on speculation is asymmetric:
- Writing 4 detailed plans on speculation: ~2 hours.
- Discovering plan-1 was wrong during implementation, re-planning, re-discussing with reviewer: ~4 hours per wrong plan.
- Net cost of speculation: ~14 hours.
- Cost of a 1-day Phase 0 triage: ~6 hours.
- Net savings: ~8 hours, AND the surviving plans are sized in concrete LOC (not ranges), AND triage typically uncovers free-bonus findings (stale docs, pre-existing bugs, design opportunities the speculation would have missed).
Context / Trigger Conditions
Use this skill when all three are true:
- You're sizing PRs against an existing codebase. (Greenfield work doesn't have anything to audit — go straight to writing-plans.)
- You don't have certainty about the codebase's current state. Markers:
- You haven't touched the relevant files this week
- Someone else is actively shipping on a branch you'll touch
- A roadmap doc claims things are "Done" with caveats
- The brainstorming output uses language like "we assume X exists" / "if Y is missing" / "her module is probably a stub" / "TBD by triage"
- The PR plans depend on those assumptions. Markers:
- LOC estimates are ranges ("150-600 LOC") instead of concrete numbers
- Plan says "PR-N sizing depends on triage findings"
- Storage / loader sizing depends on schema you haven't grep'd
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.
- 11d ago First seen · 292 lines · 40 tokens per session scan A b5347d1b8e98
pr-plan-bucket-triage-before-sizing is a skill published in the GitHub repository wan-huiyan/agent-traffic-control (3 stars, last pushed 6d ago), licensed MIT. It adds 40 tokens to every session and 3,562 once invoked, about $0.0002 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
vertical-real-estate
Residential-proptech domain knowledge so architect / pm aren't naive when speccing real-estate products (listings, lead-crm, transaction-coordination, property-mgmt). Codifies MLS/IDX reality, listing status lifecycle + syndication canonical-source, long-cycle lead nurture, transaction-coordination as the high-pain…
skeptical-triage
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.
pm-planning
Decomposition methodology for pm agent — turns an approved ARCH document into a Beads task list with explicit dependencies, time-boxes, and acceptance criteria. The pipeline can only orchestrate work it can see; this skill defines what "seeable work" looks like.
well-architected
6-pillar architecture review framework. Adapted from AWS Well-Architected for use by greatcto's architect agent on every non-nano ARCH document. Forces explicit answers across operational excellence, security, reliability, performance, cost, and sustainability — not just feature design.
product-economics
Does this product make money at a price someone will pay? Forces contribution margin, a price with a stated basis, and a bottom-up market size — each number labelled measured / assumed / unknown, so a guess can never be read as a calculation.
migration-ready-schema
Data-model rules that make a schema importable from day one, so the migration-import-engineer is never blocked on missing columns. Every SMB Product-Builder product must let a customer bring their data from an incumbent (ServiceTitan/Toast/Mindbody/Shopify) — that requires provenance (sourceref) and rollback…