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/threemoonslab/agents-shipgate/codex-skillnpx skills add ThreeMoonsLab/agents-shipgate --skill codex-skillgit clone --depth 1 https://github.com/ThreeMoonsLab/agents-shipgateWrote 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/threemoonslab/agents-shipgate/codex-skill)<a href="https://agentmods.dev/skills/threemoonslab/agents-shipgate/codex-skill"><img src="https://agentmods.dev/badge/skills/threemoonslab/agents-shipgate/codex-skill.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 | $0.00056 | $0.01521 |
| Opus 5 | $0.00028 | $0.00760 |
| Sonnet 5 | $0.00011 | $0.00304 |
| Haiku 4.5 | $0.00006 | $0.00152 |
Grade A, and why
agents-shipgate 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 4d 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.
This is a copy
98% identical to agents-shipgate — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents Shipgate
Agents Shipgate is the deterministic merge gate for AI-generated agent capability changes — a local-first, static Tool-Use Readiness review. It reads shipgate.yaml plus local tool sources and writes deterministic reports as Markdown, JSON, SARIF, and supporting Release Evidence Packets.
Use this skill when a task touches agent tools, MCP exports, OpenAPI specs, prompts that constrain tool use, permissions/scopes, approval or confirmation policies, shipgate.yaml, Shipgate CI, or agents-shipgate-reports/report.json.
Do not use it for general linting, runtime monitoring, evals, model-output quality, or runtime guardrail enforcement. Shipgate is static-only: no agent execution, no tool calls, no LLM calls, no MCP server connections, and no telemetry by default.
Workflow
- For local checks, verifier runs, host audits, and supporting recovery commands, read
references/recipes.md. - For reading
report.json, summarizing release decisions, or deciding what may be auto-applied, readreferences/report-reading.md. - Before running Shipgate CLI commands, require a CLI whose
agents-shipgate contract --jsonreportsminimum_control_contract_version: {{ minimum_control_contract_version }}: runcommand -v agents-shipgate,agents-shipgate --version, andagents-shipgate contract --json. If it is missing or stale, tell the user to install or upgradeagents-shipgate. The Codex plugin supplies workflows, not the scanner binary. - Set
AGENTS_SHIPGATE_AGENT_MODE=1before running Shipgate commands so errors include structurednext_actionJSON. - Default first-time CI to advisory mode. Do not enable release-blocking CI or save a baseline until a human has reviewed current findings.
- For local agent control, run
shipgate check --agent codex --workspace . --format agent-boundary-jsonand read the stdoutshipgate.agent_boundary_result/v2object. Switch oncontrol.state; follow onlycontrol.next_action,control.allowed_next_commands, andcontrol.human_review. Treatdecisionas diagnostic context only. - Before editing
shipgate.yaml, Shipgate CI, AGENTS/CLAUDE/Cursor rules, policy packs, baselines, waivers, suppressions, Codex hooks/config, Codex plugin manifests,.mcp.json,.app.json, orSKILL.md, plan to runagents-shipgate verifybefore completion and route trust-root review to a human when the verifier requires it. - For full PR verification, validate
agents-shipgate-reports/verification-receipt.jsonfirst, then readagent-handoff.jsonand switch oncontrol.state; readverifier.jsonfor detailed control state,verify-run.jsonfor the request graph, andreport.jsonfor reviewer detail.report.json.release_decision.decisionremains the release gate. Refresh withagents-shipgate agent control --workspace .— which refuses the read when HEAD, the tree, or the working tree has moved since the decision — before you act on any of that, and again before enforcing a cachedmust_stop, before commit/push/PR update, before merge, and before declaring the task complete. A non-zero exit means no control identity is current and you hold no authority; ifcurrent_control_idchanged, discard every cached control state and restart from the new identity. A result remembered from earlier in the conversation never outranks the current pointer, in either direction. What that command prints depends on the installed CLI, so readagents-shipgate contract --jsononce: when it reportsagent_control_schema_version,agent controlreturns that compactshipgate.agent_control/v1object —control_state,permissions,next_actor,next_action— and routing on it alone is enough, with--format pointerreturning the rawcurrent-control.json; when it does not, the CLI predates the envelope andagent controlreturns the raw pointer, whose fields arelifecycle_stateand nestedcontrol.state. - Auto-apply only high-confidence safe patches. Do not auto-assert action effect, action authority, agent bindings, approval, confirmation, idempotency, broad-scope, prohibited-action, or runtime-trace evidence.
- Ensure
.gitignorecoversagents-shipgate-reports/before committing.
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.
- 4d ago First seen · 45 lines · 56 tokens per session scan A 6c4f112551d0
agents-shipgate is a skill published in the GitHub repository ThreeMoonsLab/agents-shipgate (87 stars, last pushed 4d ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,521 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to agents-shipgate, differing in 4 lines, and is treated as a copy.
Other skills, from other repositories
release-notes
Generate GitHub release notes for the Membrane api-gateway repo by collecting the commits between the last release and master, grouping them into Features / Improvements / Fixes / Security / Dependencies, and linking each to its PR. Use whenever the user wants to draft, extract, or write release notes / a changelog /…
changelog
Invoke before committing user-facing changes (new features, bug fixes, behavior changes) to update CHANGELOG.md. Skip for internal refactors, CI, docs-only, or minor dependency bumps.
prepare-release
Prepare a release (phases 1-6). Usage: /prepare-release [version]. If version omitted, infers from conventional commits. Coordinates agents for review, runs prepare-release.sh, then enhances release notes with rich formatting.
publish-release
Publish a prepared release (phase 7). Usage: /publish-release . Requires version argument. Wraps publish-release.sh for deterministic execution.
emdash-github-actions
Sets up GitHub Actions CI/CD workflows for EmDash plugins — TypeScript type-checking, ESLint linting, Vitest testing, npm publishing, and automated releases. ALWAYS use this skill when a user wants to create, add, set up, or configure GitHub Actions, CI/CD, automated checks, or deployment workflows for an EmDash…
github-repo
Audits and improves GitHub repository quality — README structure, community health files, .github directory setup, issue/PR templates, metadata, releases, and branch hygiene. Use this skill whenever the user asks to improve, audit, review, or set up a GitHub repository, or when they mention things like "make my repo…