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 agentmods add instructions/learnprompt/skillrush-town/agents-mdgit clone --depth 1 https://github.com/LearnPrompt/skillrush-townWhat 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 | $0.00407 | $0.00407 |
| Opus 5 | $0.00204 | $0.00204 |
| Sonnet 5 | $0.00081 | $0.00081 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
skillrush-town AGENTS.md 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 2d 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.
What it actually says
Agent Instructions
This repository is maintained through the project Skill:
skills/skillrush-town/SKILL.md
Before changing data ingestion, publishing, GitHub Pages, reports, or tests, read:
skills/skillrush-town/SKILL.mdskills/skillrush-town/references/source-contract.mdskills/skillrush-town/references/source-adapter-pattern.mdskills/skillrush-town/references/publishing.mdscripts/clawhub_daily.pyREADME.md
Source Contract
Do not change the ClawHub Top100 source semantics unless the source contract is updated.
For non-ClawHub sources such as changelogs, model leaderboards, or release feeds, read skills/skillrush-town/references/source-adapter-pattern.md first and create a source-specific contract before implementation.
The canonical ranking source is:
POST https://wry-manatee-359.convex.cloud/api/query- Convex path:
skills:listPublicPageV4 - args:
sort=downloads,dir=desc,nonSuspiciousOnly=true,highlightedOnly=false,numItems=25 - pagination: follow
nextCursorfor 4 pages to build Top100
Required Headless Validation
These checks must work without browser automation:
python -m py_compile scripts/clawhub_daily.py
python -m pytest -q
For a live ingestion check, use a temporary data directory:
TMP=$(mktemp -d)
python scripts/clawhub_daily.py --date 2026-05-04 --data-dir "$TMP/data"
Optional Browser / Manual Page Check
Only run this when a browser is available:
python3 -m http.server 8093
Open:
http://127.0.0.1:8093/?date=2026-05-04
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.
- 2d ago First seen · 58 lines · 407 tokens per session scan A 7e00e4a2c275
skillrush-town AGENTS.md is an instructions file published in the GitHub repository LearnPrompt/skillrush-town (107 stars, last pushed 2d ago), licensed MIT. It adds 407 tokens to every session, about $0.0020 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 2026-08-30.
Other instructions, from other repositories
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
spring-ai-agentcore AGENTS.md
Instructions for spring-ai-community/spring-ai-agentcore, covering agents.md, project overview, architecture, key components and artifact store classes.
flyto-core CLAUDE.md
Instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
deckforge AGENTS.md
Instructions for tph-kds/deckforge, covering deckforge agent entry point, code intelligence, read order, default routing and non-negotiable implementation rules.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
agentoscope AGENTS.md
Instructions for rafaelcg/agentoscope, covering agentoscope — agent instructions, what this is, layout, commands and conventions.