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 research-lane-coordinatorgit 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/research-lane-coordinator)<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/research-lane-coordinator"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/research-lane-coordinator/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/research-lane-coordinator"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/research-lane-coordinator.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 | $0.00026 | $0.01007 |
| Opus 5.5 | $0.00010 | $0.00403 |
| Sonnet 5.5 | $0.00005 | $0.00201 |
| Haiku 4.5 | $0.00003 | $0.00101 |
Grade A, and why
research-lane-coordinator 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 1mo 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Garden
The stable invocation name remains research-lane-coordinator so existing links and task prompts keep working.
Use this as a working aid, not a fixed ceremony. Scale coordination to the question; one agent is enough when work cannot profitably split. The user's goals and current repository instructions take precedence over examples and workflow preferences here.
Start from the real state
Read the owner's goals and latest handoff, then reconcile relevant current code, merged work, open PRs, active writers and saved experiments. Keep one progress record linking each original goal to its evidence, limitation, owner and next action. A side discovery must not erase an unfinished goal.
For lane ownership, worker briefs and the boundary with a separate PR-queue coordinator, read coordination. Use the project's existing queue and release procedure. Research acceptance, merged content and verified deployment are separate claims.
For model choice, reasoning escalation, context reuse and fan-out cost, read dispatch and effort. These are choices within the host and owner’s permissions, not a fixed model ladder.
Explore different questions in parallel
Select independent angles that could change the decision: for example, whether the measurements represent the intended outcome; whether better alternatives can be constructed; whether a learned selector chooses better alternatives; and whether data/feedback reaches the next experiment intact. These are examples, not mandatory lanes.
Give each worker a bounded question, pinned baseline and inputs, owned files, evidence required, resource limit and stop condition. Include relevant prior failures and owner corrections. Use small briefs and durable artifacts rather than copying the full session into every worker. Never override a worker's higher-priority instructions to save time. Honor the host's delegation and model-selection permissions.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +2 lines fe16ccfecfd3
- 1mo ago Changed · +2 lines 8946b3ef15fe
- 1mo ago First seen · 41 lines · 26 tokens per session scan A f39bbd056369
research-lane-coordinator is a skill published in the GitHub repository wan-huiyan/agent-traffic-control (3 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 1,007 once invoked, about $0.0001 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 2026-09-13.
Other skills, from other repositories
opportunity-solution-tree
Build an Opportunity Solution Tree (OST) to structure product discovery — map a desired outcome to customer opportunities, possible solutions, and experiments. Based on Teresa Torres' Continuous Discovery Habits. Use when the team is unclear what to build next, when multiple opportunities compete, or before writing a…
done-blocked
Reusable reporting contract for any agent that hands work back to the pipeline. Forces ONE of two terminal statuses (DONE or BLOCKED) with a specific evidence shape. Stops vague "probably finished" and "kind of stuck" verdicts.
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.
project-update
Update project configuration to match the latest HCF plugin defaults. Use when the HCF plugin has been updated and you want to sync your project's config.
init
Sets up Compound V in this project. Probes git, Python, Codex, a browser runner and Superpowers; picks the reviewer and test command; writes .claude/compound-v.json and the two native project settings Compound V relies on (worktree base and run-record protection). Every write is shown as a diff and applied only on the…
conductor-orchestrator
Master coordinator for the Evaluate-Loop workflow v3. Supports GOAL-DRIVEN entry, PARALLEL execution via worker agents, BOARD OF DIRECTORS deliberation, and message bus coordination. Dispatches specialized workers dynamically, monitors via message bus, aggregates results. Uses metadata.json v3 for parallel state…