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 nwiizo/ccswarm --skill deploy-workflowgit clone --depth 1 https://github.com/nwiizo/ccswarmWrote 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/nwiizo/ccswarm/deploy-workflow)<a href="https://agentmods.dev/skills/nwiizo/ccswarm/deploy-workflow"><img src="https://agentmods.dev/badge/skills/nwiizo/ccswarm/deploy-workflow/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/nwiizo/ccswarm/deploy-workflow"><img src="https://agentmods.dev/badge/skills/nwiizo/ccswarm/deploy-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00024 | $0.00511 |
| Opus 5.5 | $0.00010 | $0.00204 |
| Sonnet 5.5 | $0.00005 | $0.00102 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
deploy-workflow 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 1mo 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploy a new ccswarm release using .github/workflows/release.yml.
The workspace has one published crate, crates/ccswarm. Follow the scope in
docs/ROADMAP.md and the version-specific notes in docs/releases/.
Pre-Deployment
# Update crates/ccswarm/Cargo.toml and its Cargo.lock package version.
# Update CHANGELOG.md and docs/releases/v<VERSION>.md.
# Quality gates
cargo fmt --all
cargo clippy --workspace --locked -- -D warnings
cargo test --workspace --locked
cargo audit
cargo doc --no-deps --workspace --locked
cargo build --release --workspace --locked
cargo publish -p ccswarm --dry-run --locked
actionlint .github/workflows/release.yml
# Browser example (installs its locked dependencies and Chromium if needed)
CCSWARM_BIN=target/release/ccswarm examples/e2e-playwright/run.sh
Build & Release
When release publication is authorized, verify the branch, remote, diff, and unused tag. Commit and push the reviewed release preparation. Run the Release workflow manually on that exact commit and verify all four native archive builds, smoke tests, and quality checks. Manual runs do not publish.
Then create and push the annotated version tag on the verified commit. The tag workflow rebuilds and validates, creates a complete draft, verifies its downloaded assets, attests the archives, publishes the stable crate, and publishes the GitHub release. Prerelease tags do not publish a crate.
Do not run a second manual publish command alongside the workflow. Verify the completed workflow, all four archives and checksums, provenance, registry version, and an installed binary before reporting success.
Failed Publication And Recovery
Inspect the failed job and current GitHub/crates.io state before retrying. The two services cannot publish atomically. A workflow retry verifies an existing crate's checksum against the candidate before skipping its upload. Investigate a mismatch rather than bypassing that check. Do not replace an already published tag or delete a published release as routine recovery. Use a follow-up version for code fixes; yanking a broken crate requires explicit authorization.
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.
- 1mo ago Changed · +9 lines e390257587f3
- 1mo ago First seen · 46 lines · 24 tokens per session scan A 84695c79ffc1
deploy-workflow is a skill published in the GitHub repository nwiizo/ccswarm (153 stars, last pushed 8d ago), licensed MIT. It adds 24 tokens to every session and 511 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
release
Fully automate a release with version-bump and childhood.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.