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 learning-loopgit 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/learning-loop)<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/learning-loop"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/learning-loop/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/learning-loop"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/learning-loop.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 | $0.00020 | $0.00539 |
| Opus 5.5 | $0.00008 | $0.00216 |
| Sonnet 5.5 | $0.00004 | $0.00108 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
learning-loop 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 — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learning Loop
Improve a decision process after a material failure, user correction or contradictory result. Use across coding, research, design and operations; an ordinary successful task or a spelling fix does not require a retrospective. The outcome can be a narrower rule, a test, a corrected measurement, or retirement of unhelpful guidance.
Learn from evidence
Read the correction procedure for a substantive correction. Preserve what happened and the exact artifact versions. Separate the observed discrepancy from its proposed cause. Reproduce or qualify that cause, find the smallest useful correction, and check both the failure and a legitimate case the correction must still allow. A tabletop review is not a measured improvement in real performance.
Put the correction where it belongs: code, data, measurement, a project decision, a skill or memory. Search existing guidance first. Keep one canonical explanation and update its retrieval descriptions and pointers; keywords appearing in a store do not prove the correction changed behavior. Preserve superseded evidence privately instead of erasing the history.
Apply supported changes within the current task's authorization. The request to improve a workflow can already authorize its local edits; do not repeatedly ask for that same permission. This skill does not authorize unrelated memory edits, changing an owner's policy, publishing future releases, or scheduled background work.
Distinguish a user's policy choice from a claimed empirical result. A user can choose a conservative restriction despite limited evidence; record its scope as a decision, without pretending one incident proves a universal mechanism. Explain the tradeoff if useful, but do not use this skill as a veto over an explicit, permissible instruction. An authorized publication still needs appropriate handling of private material; evidence uncertainty alone does not cancel publication authority.
Close the event
What ships with it
3 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 First seen · 25 lines · 20 tokens per session scan A eea2f0208b3b
learning-loop is a skill published in the GitHub repository wan-huiyan/agent-traffic-control (3 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 539 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
gan-zhong-xue
A learning workflow that makes an AI explain code changes through questions, evidence, and underlying principles. It is designed to help developers understand work they asked an AI to do, rather than merely accept the result.
help
Explain the agentic-study-environment plugin — what it does, the lifecycle skills it ships, the domain overlays, the session types, and the key conventions — or a specific one of those if the user names it. Use this skill whenever the user asks for help with the study harness itself rather than asking to study…
accessibility-audit
This skill should be used when evaluating a design, page, or component against accessibility standards and producing a severity-scored report. Trigger phrases include "audit accessibility", "check a11y", "is this accessible", "WCAG audit", "check color contrast", and "accessibility review before handoff". Use it to…
design-tokens
This skill should be used when a user wants to scaffold or refactor a design token system — e.g. "set up design tokens", "create a design system foundation", "extract these hardcoded colors into tokens", "add a type scale", "theming setup", or "dark mode tokens". It produces a single source of truth for color, type…
explain
Explain what a piece of code does — a specific file, class, or method in close detail, or a user-facing flow as a concise system overview. What it does and why, not whether it's good.
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.