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/mgiovani/cc-arsenal/oss-launchnpx skills add mgiovani/cc-arsenal --skill oss-launchgit clone --depth 1 https://github.com/mgiovani/cc-arsenalWrote 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/mgiovani/cc-arsenal/oss-launch)<a href="https://agentmods.dev/skills/mgiovani/cc-arsenal/oss-launch"><img src="https://agentmods.dev/badge/skills/mgiovani/cc-arsenal/oss-launch.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 | $0.00218 | $0.02451 |
| Opus 5 | $0.00109 | $0.01226 |
| Sonnet 5 | $0.00044 | $0.00490 |
| Haiku 4.5 | $0.00022 | $0.00245 |
Grade A, and why
oss-launch 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 6d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OSS Launch
Take a private side project from "done" to a public GitHub launch in seven staged gates: pre-flight, review, brand, README, mention scrub, history rewrite (optional, hard-gated), public flip. Like ship, every stage reports the real command it ran and the run stops at the first gate that isn't met: never estimate a result, never skip a gate silently.
Track progress with TodoWrite (one line per stage) so the user sees where the launch train is if a gate stops it.
The stages
| # | Stage | Gate |
|---|---|---|
| 1 | Pre-flight | Repo is private; no leaked secrets; a license exists |
| 2 | Review | No unresolved Critical/High findings |
| 3 | Brand | (optional) logo/hero generated or reused |
| 4 | README + description | Value-prop-first README, topics set |
| 5 | Mention scrub | User confirms exactly what gets removed |
| 6 | History rewrite | Private only, ever-public check, explicit confirmation this turn |
| 7 | Public flip | Every earlier stage passed |
Stage 1: Pre-flight
gh repo view --json isPrivate,licenseInfo,forkCount,stargazerCount -q .: recordisPrivate; this is the launch's core assumption and Stage 6 rechecks it independently.- Secrets scan: run the same check
env-setup's Phase 6 does, grep tracked files and.env/git history for key/secret/password/token patterns (see that skill'sscan-patterns.mdreference if you need the full pattern set). Any hit stops the whole train: report the finding asfile:lineonly, never the matched value, and go no further. - License: check for
LICENSE/LICENSE.md/COPYINGat the repo root. Missing license is not an auto-fill, ask the user which license they want (MIT, Apache-2.0, etc.) before continuing; don't pick one for them.
Stage 2: Review
Invoke the review-code skill (via Skill, or a Task/Explore→sonnet subagent if that's unavailable) against the default branch. Any Critical/High finding stops the train: report it and let the user decide (fix and re-run, or explicitly accept the risk). Medium/Low findings are reported but don't block.
What ships with it
5 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.
- 6d ago First seen · 127 lines · 218 tokens per session scan A 53e16ddfddd0
oss-launch is a skill published in the GitHub repository mgiovani/cc-arsenal (7 stars, last pushed 6d ago), licensed MIT. It adds 218 tokens to every session and 2,451 once invoked, about $0.0011 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
commit-pr
Mandatory Codex/Copilot publication adapter for opencode-swarm. Use for every GitHub issue assignment that results in code changes, commits, pushes, draft PRs, PR body edits, PR readying, release notes, or CI closeout. Must be loaded before git push, gh pr create, gh pr edit, or gh pr ready. Routes to the single…
contributing
Codex adapter for the opencode-swarm contribution checklist. Use when preparing user-visible changes, release note fragments, local validation, branch hygiene, PR checklist items, or contribution-policy compliance before publishing work.
release
Prepare code for release (version bumps, changelog, README updates) and create an annotated tag to trigger the GoReleaser workflow.
forgejo-cli
Use when managing a Forgejo or Gitea server from the terminal: issues, pull requests, repositories, file contents, labels, milestones, releases, webhooks, user settings, or any /api/v1 endpoint through a safe generic API command. Do not use this skill for unrelated requests; route to the nearest named specialist.
release-engineering
Design, automate, and operate end-to-end software releases: release process models and pipelines (trunk-based development, CD stages, release trains), progressive delivery and feature flags, versioning and artifact management (SemVer, conventional commits, changelogs, SBOM/provenance), readiness and quality gates…
verified-delivery
Implement and deliver an authorized change end to end — verify, open the PR, merge, and confirm post-merge state — using live-state gates, durable interruption handoffs, and live-state-first resumption. Use when a user grants end-to-end delivery authority for a specific change and the work may cross tool-call limits…