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 mirkobozzetto/arsenal --skill shipgit clone --depth 1 https://github.com/mirkobozzetto/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/mirkobozzetto/arsenal/ship)<a href="https://agentmods.dev/skills/mirkobozzetto/arsenal/ship"><img src="https://agentmods.dev/badge/skills/mirkobozzetto/arsenal/ship/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/mirkobozzetto/arsenal/ship"><img src="https://agentmods.dev/badge/skills/mirkobozzetto/arsenal/ship.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 | $0.00035 | $0.01447 |
| Opus 5.5 | $0.00014 | $0.00579 |
| Sonnet 5.5 | $0.00007 | $0.00289 |
| Haiku 4.5 | $0.00003 | $0.00145 |
Grade A, and why
ship 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship
Own the result, not a ceremony. A clear request is sufficient authorization for its reversible, in-scope implementation. Do not ask whether to start. Do not turn a small fix into a brief, proposal, interview, or document bundle.
Execution policy
- Work solo. Ask before every proposed delegation, including reviews. State the independent scope and expected benefit. Auto mode never grants consent.
- Use the active model and configured routing. Do not inspect or tune models during an unrelated task. No hidden advisor or nested delegation.
- Read the relevant existing code, fix the cause, run the smallest meaningful behavioral check, and deliver. Reuse current evidence until code or inputs relevant to that evidence change. No routine full-file read-back.
- Keep backups and explicit approval for live data, destructive operations, publication, and deployment. A build target may install or deploy; inspect its actual effects instead of trusting its name.
- Stop on user interruption. A completed task is not reopened by a reminder.
Efficiency plugins such as Espresso are optional. Their automatic mode does not waive Ship's per-delegation consent, solo mode, specialist/model choices, artifact gates, verification or commit rules. Do not add a parallel team or reviewer. Without the plugin, Ship behaves unchanged.
Choose the shortest sufficient path
Clear request: identify the target and success condition from the request and existing code. Ask only for a missing decision that materially changes the result. Implement directly; no mandatory artifact files or step-by-step gates.
Approved spec: read the exact artifact once. Brief requires ready;
proposal requires explicit Accepted. Honor scope, dependencies, acceptance
criteria and non-goals. A shipped marker means done, not another run. On the
first run of a spec in a Git repository, work on its branch created from
origin/<base> (steps/step-00-init.md); a task that carries an issue is
read together with that issue's Pickup Directive.
What ships with it
17 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.
- references/guardrails.md 1.1 KB
- references/help-text.md 1.2 KB
- references/role-templates.md 976 B
- scripts/detect-stack.sh 1.0 KB runs code
- scripts/scaffold.sh 347 B runs code
- steps/step-00-init.md 3.4 KB
- steps/step-00-triage.md 395 B
- steps/step-01-ingest.md 722 B
- steps/step-02-plan.md 1.1 KB
- steps/step-03-engine.md 698 B
- steps/step-04-execute.md 824 B
- steps/step-05-verify.md 806 B
- steps/step-06-finish.md 5.2 KB
- templates/contract.md 173 B
- templates/state.yaml 177 B
- templates/trace.md 271 B
- templates/verification-bundle.md 256 B
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 38f2275f5be2
- 1mo ago Changed · +8 lines aff5cd913f0d
- 1mo ago Changed · +27 lines 0ffab3820899
- 1mo ago Changed · +2 lines c8fcdf6a2a2e
- 1mo ago Changed · -64 lines · -146 tokens per session scan C → A 7d8e98865190
- 1mo ago First seen · 145 lines · 181 tokens per session scan C 55bb17f931b2
ship is a skill published in the GitHub repository mirkobozzetto/arsenal (22 stars, last pushed 8d ago), licensed MIT. It adds 35 tokens to every session and 1,447 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
give-me-tips
Explains any senpi tip in depth, including Tip: lines in the TUI. Use when the user asks about a tip, what a tipped feature does, or which tips they can see.
switch-clients
Switch between existing customer engagements and triage competing needs. Use when context switching causes confusion; requires engagement records and preserves one client per write.
Prompt Version Control Workflow
Sets up a prompt versioning system with naming conventions, diff tracking, A/B evaluation gates before promotion, and rollback triggers.
Changelog Curator
Maintains and formats a CHANGELOG.md following Keep a Changelog conventions from git history or PR list.
PR Description Writer
Writes clear, thorough pull request descriptions from a diff or list of changes.
Release Notes Generator
Generates clear, user-friendly release notes from a git log or list of PRs.