Borrowing it
Nothing to install: this file belongs to greenmtnsun/GitEasy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/greenmtnsun/GitEasy/main/.claude/skills/swarm-ready/SKILL.mdgit clone --depth 1 https://github.com/greenmtnsun/GitEasyWrote 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/greenmtnsun/giteasy/swarm-ready)<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/swarm-ready"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/swarm-ready/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/greenmtnsun/giteasy/swarm-ready"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/swarm-ready.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 | $0.00123 | $0.02773 |
| Opus 5.5 | $0.00049 | $0.01109 |
| Sonnet 5.5 | $0.00025 | $0.00555 |
| Haiku 4.5 | $0.00012 | $0.00277 |
Grade A, and why
swarm-ready 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 today.
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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
See also:
phase-gate(phases),goal-author(GRs),dr-author(DRs),virtual-uml-architect(UML-as-contract),virtual-tester+ PesterForge (tests),honest-completion(evidence citation),verify-claims-on-disk(trust-but-verify on apply claims),software-creation§8 (phase model).
Swarm-ready project standard
A project is swarm-ready when multiple agents can fan out across it — sweeps, parallel sub-agents, "go nuts" — fast and safely, because the work is decomposed, documented, and verifiable without a human in the loop for every step.
This skill is the reusable discipline (the bar). The concrete artifacts that satisfy it live inside each project's own repo. Same shape as phase-gate (a shared skill) producing Docs/PHASE.txt (a per-repo file).
Scope discipline — read this first
Products are separate. This skill never crosses a project boundary. It assesses or remediates exactly one project — or one broken-out subproject — at a time, using only that project's own files. There is no suite-wide swarm-ready document, no cross-project registry, no shared artifact. The only thing shared is this skill itself, because a skill is Claude tooling, not a project. If a session ever pulls a swarm-ready artifact from a sibling project, that is a bug — flag it, don't act on it.
The bar — six requirements
A project is swarm-ready only when all six hold. Each is scored with cited evidence (see §6), never by assertion.
1. Tests, hard
- Native framework: Pester for PowerShell; the project's own framework otherwise (xUnit for C#, Vitest for TypeScript / Forge).
- Every public function/unit has at least one real test — real-function-pattern, not mock-only theater.
- Tiered REAL / AI-INFERRED / STUB per PesterForge; STUBs disclosed, never silent.
- CI green on every runtime the project claims (e.g. PS 5.1 and PS 7).
- "Pester the crap out of it" = the public surface and the failure paths, not just the happy path.
2. Work structure
- Decisions in
Docs/DECISIONS_PHASE<N>.md(dr-author). - Goals in
Docs/Goals/GR-NNN-*.mdwith aDocs/GOALS.mdindex (goal-author). - Active phase in
Docs/PHASE.txt(phase-gate). Phase model is project-defined.
What ships with it
1 file 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.
- today First seen · 102 lines · 0 tokens per session scan A 1e5485358d2f
swarm-ready is a skill published in the GitHub repository greenmtnsun/GitEasy (1 stars, last pushed yesterday), licensed MPL-2.0. It adds 123 tokens to every session and 2,773 once invoked, about $0.0005 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 2026-11-18.
swarm-ready compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| swarm-readygreenmtnsun/GitEasy | Skill | 1 | yesterday | MPL-2.0 | A | 123 | Claude Code |
| imagegenopenai/codex | Skill | 136k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 101k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 395k | today | MIT | A | 36 | Claude Code |
| free-llm-apismnfst/awesome-free-llm-apis | Skill | 14k | today | CC0-1.0 | A | 113 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | today | MIT | A | 95 | Claude Code |