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 flyingsquirrel0419/squirrel-skill --skill squirrelgit clone --depth 1 https://github.com/flyingsquirrel0419/squirrel-skillWrote 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/flyingsquirrel0419/squirrel-skill/squirrel)<a href="https://agentmods.dev/skills/flyingsquirrel0419/squirrel-skill/squirrel"><img src="https://agentmods.dev/badge/skills/flyingsquirrel0419/squirrel-skill/squirrel.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 5.1 | $0.00204 | $0.06328 |
| Opus 5 | $0.00102 | $0.03164 |
| Sonnet 5 | $0.00041 | $0.01266 |
| Haiku 4.5 | $0.00020 | $0.00633 |
Grade A, and why
squirrel 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 7d 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 — 625 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🐿️ Squirrel — Full-Cycle Software Development Skill
Squirrel works on any project at any stage — from blank canvas to legacy codebase. The first thing it does is figure out where the project actually is, then jump in at exactly the right point.
Step 0 — Detect Mode (Always First)
Before anything else, answer: Is this a new project or an existing one?
# Check for signs of an existing codebase
ls -la
find . -maxdepth 2 \( -name "package.json" -o -name "pyproject.toml" -o -name "go.mod" \
-o -name "Cargo.toml" -o -name "Gemfile" -o -name "*.csproj" \) 2>/dev/null
find . -maxdepth 1 -name "*.md" 2>/dev/null
| Signal | Mode |
|---|---|
| Empty dir, no source files | 🆕 Greenfield — start from scratch |
| Source files exist, no tests, no docs | 🔧 In-Progress — join and improve |
| Source + tests + CI + README | 🏗️ Mature — targeted improvement |
| "fix this bug / add this feature / review my code" | 🎯 Targeted — scoped task, full audit optional |
Announce the mode to the user: "This looks like an in-progress project — I'll audit the existing code before touching anything."
Each mode has a different entry point into the phases below. Don't always start at Phase 1.
Phases
[1] 🔍 Discover → Understand the project (new OR existing)
[2] 📋 Plan → Decide what to do and in what order
[3] 💻 Build → Write or modify code
[4] 🧪 Test → Run + write tests
[5] 🐛 Bug Hunt → Static analysis + manual review
[6] ✨ Polish → Lint + format + type check
[7] 📖 Document → README + inline docs
[8] 🚀 Ship → Final review, clean deliverable
Greenfield projects: run all 8 phases in order.
In-Progress / Mature projects: always run Phase 1 (Audit) first, then jump to whichever phases are relevant to the task. You don't need to rebuild tests that already exist or rewrite docs that are already good — but you do need to know they exist before skipping them.
What ships with it
4 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.
- 7d ago First seen · 625 lines · 204 tokens per session scan A c9f24ebb5f61
squirrel is a skill published in the GitHub repository flyingsquirrel0419/squirrel-skill (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 204 tokens to every session and 6,328 once invoked, about $0.0010 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
qa
QA test your code changes by reading your git diff, choosing the right validation path for frontend/browser and backend changes, and reporting pass/fail with evidence.
cross-repo-testing
This skill should be used when the user asks to "test a cross-repo feature", "deploy a feature branch to staging", "test SDK against OH Cloud", "e2e test a cloud workspace feature", "test provider tokens", "test secrets inheritance", or when changes span the SDK and OpenHands server repos and need end-to-end…
antigravity-tla-guard
Implements formal mathematical verification for Python AI agents. Use when generating agent code like PydanticAI or LangGraph, or when user asks to add TLA+ verification, make the agent safe, prevent hallucinations, or implement antigravity guardrails.
faf-skills
17 Claude Code skills for AI-context, testing, and MCP development. IANA-registered format (application/vnd.faf+yaml). Create .faf project DNA, score AI-readiness (0-100%), sync with CLAUDE.md, build MCP servers, generate test suites. 36,000+ downloads across npm, PyPI, crates.io.
cline-fix-volatile-msg
Ladder-aware Cline Anthropic caching — verify the rolling read/write ladder on the wire, then add the tools breakpoint and tune TTL. Updated for the 2026-08 AI-SDK monorepo.
continue-gemini-explicit
Continue's Gemini provider doesn't use the cachedContents API at all. Add explicit caching for sessions over the minimum token threshold.