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 miopea/swarm-legacy --skill swarm-checkpointgit clone --depth 1 https://github.com/miopea/swarm-legacyWrote 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/miopea/swarm-legacy/swarm-checkpoint)<a href="https://agentmods.dev/skills/miopea/swarm-legacy/swarm-checkpoint"><img src="https://agentmods.dev/badge/skills/miopea/swarm-legacy/swarm-checkpoint/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/miopea/swarm-legacy/swarm-checkpoint"><img src="https://agentmods.dev/badge/skills/miopea/swarm-legacy/swarm-checkpoint.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 | $0.00057 | $0.00738 |
| Opus 5 | $0.00028 | $0.00369 |
| Sonnet 5 | $0.00011 | $0.00148 |
| Haiku 4.5 | $0.00006 | $0.00074 |
Grade A, and why
swarm-checkpoint 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 11d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/swarm-checkpoint — Validate and commit progress
Use this skill to checkpoint your work mid-task. It runs the project's validation suite, and based on the result either commits cleanly OR reports a blocker without committing.
Workflow
Step 1 — Run validation
Invoke the project's pre-commit validation via the /check slash command. This runs format + lint + tests. ALL must pass with zero warnings.
If /check is not available in this project, run the equivalent: format + lint + test suite as defined in CLAUDE.md or the project manifest (pyproject.toml, package.json, Makefile, etc.).
Step 2A — On PASS
- Call
mcp__swarm__swarm_report_progresswithphase="checkpointing"and a reasonable percent estimate based on overall task progress. - Run
git status --shortandgit diff --statto identify exactly which files you intentionally changed. - Stage only the files you changed for this checkpoint, by name. NEVER use
git add -Aorgit add .— that risks committing unintended files (.env, build artifacts, sibling work). - Generate a concise commit message following the project's conventions. Use the project's
/commitslash command if present; otherwise commit manually with a HEREDOC body following Conventional Commits unlessCLAUDE.mdsays otherwise. - Make the commit. Do NOT push unless the user has explicitly asked you to.
- Report a one-line confirmation, e.g.
Checkpoint committed: <short hash> "<subject>".
Step 2B — On FAIL
- Call
mcp__swarm__swarm_report_progresswithphase="blocked", your current percent estimate, andblockersset to a brief description of what's failing (e.g.,lint: 3 errors,tests: 2 failing in test_foo.py). - Call
mcp__swarm__swarm_note_to_queenwith the failure output (truncated to ~600 chars) so the Queen can see what's blocking. - STOP. Do not commit. Do not auto-create a fix-up task. Do not start a partial fix unless the user explicitly asks.
- Report a one-line summary, e.g.
Checkpoint blocked: <reason>. Note sent to Queen.
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.
- 11d ago First seen · 50 lines · 57 tokens per session scan A 5183cf9cb3f6
swarm-checkpoint is a skill published in the GitHub repository miopea/swarm-legacy (9 stars, last pushed 12d ago), licensed MIT. It adds 57 tokens to every session and 738 once invoked, about $0.0003 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
oma-scm
SCM (software configuration management) and Git: branching, merges, conflicts, worktrees, baselines, audit readiness, plus Conventional Commits and safe staging.
smart-commit
Analyzes all uncommitted changes (staged and unstaged), groups them into atomic commits by logical purpose, and generates clear conventional commit messages with practical, context-rich bodies. Use when the user asks to "smart commit", "group my commits", "split into atomic commits", "organize my changes into…
scan-commit
Automatically scan the repository for unstaged/untracked changes, group them into logical commits using hunk-level analysis, stage and commit them following Conventional Commits.
create-pr
Rebase from the latest origin/main, squash the commits from it, and then create a PR on github with intelligent commit messages based on staged changes.
smart-commit
Analyze staged changes and split them into multiple logical commits following Conventional Commits.
gen-commit-msg
Generate intelligent commit messages based on staged changes following Conventional Commits format.