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 skills/dannote/dot-pi/skill-discoverynpx skills add dannote/dot-pi --skill skill-discoverygit clone --depth 1 https://github.com/dannote/dot-piWrote 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/dannote/dot-pi/skill-discovery)<a href="https://agentmods.dev/skills/dannote/dot-pi/skill-discovery"><img src="https://agentmods.dev/badge/skills/dannote/dot-pi/skill-discovery.svg" alt="Measured on agentmods" 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 | $0.00014 | $0.00830 |
| Opus 5 | $0.00007 | $0.00415 |
| Sonnet 5 | $0.00003 | $0.00166 |
| Haiku 4.5 | $0.00001 | $0.00083 |
Grade A, and why
skill-discovery 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 5d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Discovery
Find agent skills on GitHub using gh CLI. Skills work across multiple harnesses (Claude Code, Codex, Gemini CLI, Pi, etc.) as they follow the same SKILL.md format.
Workflow
- Search repos by topic to find skill collections
- For awesome lists: fetch README and extract skill links
- For skill repos: list directories containing SKILL.md
- Build searchable catalog at
/tmp/skills-catalog.md - Search/filter based on user query
Find skill repos
gh search repos --topic=claude-skills --sort=stars --limit=30 --json fullName,description
gh search repos --topic=codex-skills --sort=stars --limit=20 --json fullName,description
gh search repos --topic=gemini-skills --sort=stars --limit=20 --json fullName,description
gh search repos --topic=skill-md --sort=stars --limit=20 --json fullName,description
gh search repos --topic=agent-skills --sort=stars --limit=20 --json fullName,description
gh search repos --topic=claude-code-skills --sort=stars --limit=20 --json fullName,description
gh search repos --topic=gemini-cli-skills --sort=stars --limit=20 --json fullName,description
Find repos with SKILL.md files
Search GitHub code for actual SKILL.md files (finds repos not tagged with topics):
# Find repos containing SKILL.md files, then fetch stars via GraphQL (single query)
repos=$(gh search code "filename:SKILL.md" --limit=50 --json repository | jq -r '.[].repository.nameWithOwner' | sort -u)
# Build GraphQL query to get stars for all repos at once
query="{ "
i=0
for repo in $repos; do
owner="${repo%/*}"
name="${repo#*/}"
query+="r$i: repository(owner: \"$owner\", name: \"$name\") { nameWithOwner stargazerCount description } "
((i++))
done
query+="}"
gh api graphql -f query="$query" --jq '.data | to_entries[] | "\(.value.nameWithOwner) ★\(.value.stargazerCount) - \(.value.description // "no desc")"' | sort -t'★' -k2 -rn
Build catalog from awesome lists
For repos with "awesome" in name, fetch README:
gh api "repos/<owner>/<repo>/contents/README.md" --jq '.content' | base64 -d >> /tmp/skills-catalog.md
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.
- 5d ago First seen · 100 lines · 14 tokens per session scan A 050968bfa7df
skill-discovery is a skill published in the GitHub repository dannote/dot-pi (51 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 830 once invoked, about $0.0001 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 skills, from other repositories
a0-development
Development guide for extending Agent Zero from current source and DOX. Use for framework architecture, tools, extensions, API/WebUI handlers, agent profiles, prompts, skills, projects, runtime boundaries, and contribution workflow. Load the focused reference files before giving implementation guidance.
skill-author
Teach an author how to integrate the CAFleet-orchestrated team pattern into a new skill they are writing. Auto-load when the author intends to create a new CAFleet-orchestrated skill, write a skill that spawns cafleet members, add a Director/Member team skill, design a multi-agent broker-coordinated skill, build a…
clean-docs
Clean up the repository's docs, comments, rules, and tests as a CAFleet team of disjoint-slice scanner members gated by a reviewer — exactly one workflow per run. Use the residue workflow when the user asks to clean up historical narration or historical residue, remove deprecation notes / "this replaces X" / "renamed…
cafleet
Interact with the CAFleet message broker and supervise CAFleet member teams. Use when an agent needs to register as a member, send/receive messages, poll inbox, acknowledge messages, or discover other members; or when a Director is about to spawn, monitor, health-check, or recover a stalled team of CAFleet members…
temporal-developer
Develop, debug, and manage Temporal applications across Python, TypeScript, Go, Java, .NET, Ruby, and Rust. Use when the user is building workflows, activities, or workers with a Temporal SDK, debugging issues like non-determinism errors, stuck workflows, or activity retries, using Temporal CLI, Temporal Server, or…
anycap-human-interaction
Collect structured visual feedback from humans using AnyCap's annotation tool, or create and iterate on diagrams using the interactive whiteboard (Excalidraw). Covers image annotation, URL/web page review with screen recording, video review, audio feedback, and collaborative diagramming with Mermaid input. Use when…