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 rafmacalaba/armada --skill armada-voyage-finishgit clone --depth 1 https://github.com/rafmacalaba/armadaWrote 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/rafmacalaba/armada/armada-voyage-finish)<a href="https://agentmods.dev/skills/rafmacalaba/armada/armada-voyage-finish"><img src="https://agentmods.dev/badge/skills/rafmacalaba/armada/armada-voyage-finish/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/rafmacalaba/armada/armada-voyage-finish"><img src="https://agentmods.dev/badge/skills/rafmacalaba/armada/armada-voyage-finish.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 | $0.00058 | $0.00445 |
| Opus 5 | $0.00029 | $0.00222 |
| Sonnet 5 | $0.00012 | $0.00089 |
| Haiku 4.5 | $0.00006 | $0.00044 |
Grade A, and why
armada-voyage-finish 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 10d 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.
What it actually says
Armada: Voyage Finish
The finalization ritual one voyage closes. Loaded by the orchestrator at voyage-end, then dispatched to a galleon subagent as its task prompt. One-shot, ordered, PR-first.
Steps (strict order, stop on failure)
- Rebase.
git fetch originthengit rebase origin/master. Fast-forward only. If not a fast-forward, STOP and report to the orchestrator — never force-rebase, never merge. - TODO PR fix. For each feature this lane shipped, replace its
(#<pending>)placeholder inTODO.mdwith(#<PR>)using the real PR number fromgh pr view --json number. - Regen scaffold.
node src/cli.js init --from-armada armada/armada.yaml --target <lane>soAGENTS.md,REQUIREMENTS.md, and agents stay in sync withsrc/. TheAGENTS.mdvoyage header must not be re-titled. - Commit + push. Commit the regen + TODO fix on the lane branch and push to origin. Never commit on master.
- Open/update PR.
gh pr create --base master --title ... --body ...(orgh pr editif the PR already exists). Record the PR URL.
Forbids
- Never edit
armada/REQUIREMENTS.md. - Never close the voyage or mark any feature done.
- Never
git mergelocally, never push master directly. - Never run
npm publish. - Never edit files owned by other voyages or running phases.
Example: dispatch a galleon with this whole body as its task prompt; it executes step 1-5 and returns either a PR URL or the blocker that stopped it.
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.
- 10d ago First seen · 26 lines · 0 tokens per session scan A 91027ecb7ed0
armada-voyage-finish is a skill published in the GitHub repository rafmacalaba/armada (96 stars, last pushed 12d ago), licensed MIT. It adds 58 tokens to every session and 445 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 2026-08-30.
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.
safe-extraction
Apply when extracting code from a large monolith file into submodules. Covers barrel re-exports, internals DI seam proxy patterns, CI invariant allowlist updates, and cross-file test verification. Prevents CI failures, broken imports, and test regressions from code extraction.
git-revert-safety
Apply when reverting commits, undoing merges, or recovering from branch contamination. Covers collateral damage verification (manifest, package.json, CHANGELOG, lockfiles), cherry-pick vs revert decision matrix, partial-revert detection, merge-parent handling, and post-revert CI verification. Prevents the most common…
parallel-work-check
Apply before starting work on an existing branch. Checks for parallel work by other agents or developers that may supersede or conflict with your planned changes. Prevents wasted effort on stale branches.
fork-pr-operations
Operational patterns for fork PRs (head repo differs from base repo). Covers GitHub workflow approval after push, force-push protocol, remote naming conventions, stale CI verification, and bot review multi-round awareness. Load when working with fork PRs, cross-repo contributions, or workflow approval issues.