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 Ezra144israel/governed-agent-skills --skill ship-it-or-fix-itgit clone --depth 1 https://github.com/Ezra144israel/governed-agent-skillsWrote 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/ezra144israel/governed-agent-skills/ship-it-or-fix-it)<a href="https://agentmods.dev/skills/ezra144israel/governed-agent-skills/ship-it-or-fix-it"><img src="https://agentmods.dev/badge/skills/ezra144israel/governed-agent-skills/ship-it-or-fix-it/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/ezra144israel/governed-agent-skills/ship-it-or-fix-it"><img src="https://agentmods.dev/badge/skills/ezra144israel/governed-agent-skills/ship-it-or-fix-it.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 | $0.00098 | $0.04648 |
| Opus 5 | $0.00049 | $0.02324 |
| Sonnet 5 | $0.00020 | $0.00930 |
| Haiku 4.5 | $0.00010 | $0.00465 |
Grade A, and why
ship-it-or-fix-it 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 12d 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 — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship It or Fix It
Progressive activation and mutual exclusion
Use the smallest production-completion level that fits the task:
- Level 0, ordinary work: factual answers, analysis, diagnosis, review-only work, formatting, generated refreshes, and non-executable documentation use proportional verification only.
- Level 1, governed completion: material production code or configuration
changes use the existing
governed-operatorBuilder and independent final Reviewer path. Do not load or claimship-it-or-fix-itat this level. - Level 2, Ship It or Fix It: load this skill ONLY per the Governance
Dial in
governed-operator: a direct operator instruction setting G2 for the current or named work unit, a direct imperative naming this skill for the work unit, or a resumed work unit whose durablegovernance_levelrecord is already G2. Task class alone, including security, privacy, authentication, authorization, payments, destructive operations, irreversible migration, cross-system authority, or production publication, NEVER auto-activates this level; those tasks default to Level 1 with its integrity floor. If this level seems warranted and the operator has not set it, ask once (one line: risk at the current level, cost of this level); an unanswered question changes nothing and creates no stop. Discussion, quotation, or questions about this skill activate nothing.
The operator may explicitly stop this skill at any time; lowering is a prospective operator transition that preserves produced evidence. If risk classification is uncertain, perform the smallest read-only check needed to frame the dial question; do not load the full skill merely to classify the task. This skill never grants commit, publication, installation, deployment, account, or product-Done authority.
Exactly one completion workflow may be enabled for a task, and the frozen
Outcome Contract names it. If another self-review or repair-loop workflow
appears enabled beside this skill, stop before candidate work and return
RECONVERGE.
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.
- 12d ago First seen · 429 lines · 98 tokens per session scan A d20caad4d590
ship-it-or-fix-it is a skill published in the GitHub repository Ezra144israel/governed-agent-skills (21 stars, last pushed 4d ago), licensed MIT. It adds 98 tokens to every session and 4,648 once invoked, about $0.0005 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
hinge-profile-optimizer
Improve a Hinge dating profile through research-backed screenshot audits, photo selection and ordering, conversational discovery, prompt and caption writing, settings review, or post-launch troubleshooting. Use for a full profile rebuild or a focused request about photos, copy, positioning, match quality, or profile…
sanctifai
Human-in-the-loop skill for AI agents. Use when your agent needs humans to review, approve, or complete a task. Provides REST API and MCP (Model Context Protocol) integration with long-polling and webhooks. No server required — agents self-register and get responses back asynchronously.
concept-audit
A read-only audit skill for checking code against Daniel Jackson concept models, which describe independent parts of a system and how they work together.
gemini-cli-agent
Gemini CLI sub-agent system for cost-efficient analysis using the gemini binary. Use when piping large contexts to cheaper Google Gemini models (gemini-3-flash-preview, gemini-3.1-pro-preview) for security audits, architecture reviews, or QA analysis. For frontier models (Gemini 3.8 Flash and above), use agy-cli-agent…
proof-of-human
Use this whenever an agent must prove a qualified human participated — bind points, approvals, regulated actions, or sending work outside the session. Obtains cryptographic Proof of Human (WebAuthn-backed attestation + portable certificateurl) on demand. When WebAuthn cannot run in-card, mint via this Chat bridge…
update-llms
Updates the llms.txt file to reflect changes in documentation. Use when editing repository details or specifications. For creating from scratch, see create-llms.