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 benrben/MPGA --skill shipgit clone --depth 1 https://github.com/benrben/MPGAWrote 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/benrben/mpga/ship)<a href="https://agentmods.dev/skills/benrben/mpga/ship"><img src="https://agentmods.dev/badge/skills/benrben/mpga/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/benrben/mpga/ship"><img src="https://agentmods.dev/badge/skills/benrben/mpga/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 | $0.00027 | $0.01426 |
| Opus 5.5 | $0.00011 | $0.00570 |
| Sonnet 5.5 | $0.00005 | $0.00285 |
| Haiku 4.5 | $0.00003 | $0.00143 |
Grade A, and why
mpga-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 2mo 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ship
Trigger: All tasks verified and ready to commit. Time to SHIP. The most satisfying moment in software development. All tests pass — very successful! Make Project Great Again.
Protocol
Phase 1 — Parallel pre-ship checks (Ship Gate)
Run ALL of the following checks simultaneously. Every check must pass before proceeding. If ANY check fails, report which ones failed and STOP — do not commit broken code.
Run these in parallel (all at once, not sequentially):
-
Tests pass — run the full test suite:
pytest -
Ruff passes — zero lint errors across the full project:
.venv/bin/ruff check .If ruff is not installed, treat this check as passed.
-
Evidence drift check — no stale evidence links:
mpga drift --quick -
visual regression clean — UI tasks only:
- Run the
visual-testergate when the completed work touched UI files - Non-UI tasks skip this check entirely
- Run the
-
ui-audit passed — UI tasks only:
- Run
mpga-ui-auditor confirm the latest ui-auditor pass - Non-UI tasks skip this check entirely
- Run
-
No uncommitted scope changes — scope files must be clean:
git diff --name-only -- 'MPGA/scopes/' 'mpga-plugin/cli/MPGA/scopes/'If this returns any files, the check FAILS. Scope docs must be committed or staged before shipping.
Ship Gate decision:
- ALL checks pass → proceed to Phase 2
- ANY check fails → print a summary table of pass/fail results for each check, then STOP
Example gate output:
Ship Gate Results:
[PASS] Tests pass (pytest)
[PASS] Ruff clean (ruff check .)
[FAIL] Evidence drift — 3 stale links found
[PASS] visual regression clean (UI task only)
[PASS] ui-audit passed (UI task only)
[PASS] No uncommitted scope changes
BLOCKED: 1 check failed. Fix issues before shipping.
Phase 2 — Update scope evidence
- Check task cards for
evidence_producedfields - Add any missing evidence links to scope docs — COMPLETE documentation
- Run evidence verification to confirm:
mpga evidence verify
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.
- 2mo ago First seen · 174 lines · 27 tokens per session scan A dcc9ca1ac369
mpga-ship is a skill published in the GitHub repository benrben/MPGA (5 stars, last pushed 7mo ago), licensed MIT. It adds 27 tokens to every session and 1,426 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 2026-09-03.
mpga-ship compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mpga-shipbenrben/MPGA | Skill | 5 | 7mo ago | MIT | A | 27 | Claude Code |
| release-announcementpaperclipai/paperclip | Skill | 113k | today | MIT | A | 42 | Claude Code, Codex |
| release-notesphuryn/pm-skills | Skill | 28k | 3d ago | MIT | A | 57 | Claude Code |
| releasethedotmack/claude-mem | Skill | 116k | today | Apache-2.0 | A | 13 | Claude Code |
| multi-agent-release-managerchromium/chromium | Skill | 25k | today | BSD-3-Clause | A | 27 | Claude Code, Codex |
| pack-submitaeonfun/aeon | Skill | 791 | today | MIT | A | 27 | Claude Code, Codex |
| updater_guidesiddsachar/row-bot | Skill | 1.7k | today | Apache-2.0 | A | 22 | Claude Code, Codex |