protocol

A required procedure for coding agents that use Agents Shipgate, a local governance check for changes that affect agent capabilities. It defines the command and JSON result used for the check.

In plain words
What is it for?
Running local or committed-diff checks for changes to agent behavior, and producing evidence for continuous integration or code review.
Why use it?
It gives agents a consistent way to verify that capability-related changes meet the project's governance rules before completion.

Agent

Install

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.

agentmods
npx agentmods add agents/threemoonslab/agents-shipgate/protocol
Clone the repo
git clone --depth 1 https://github.com/ThreeMoonsLab/agents-shipgate
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,818 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.03818
Opus 5 $0.00000 $0.01909
Sonnet 5 $0.00000 $0.00764
Haiku 4.5 $0.00000 $0.00382

Measured yesterday against content hash 510f9b2c165c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

protocol 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 yesterday.

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.

docs/agents/protocol.md · 379 lines

How it starts

The opening of the file, as written. The whole thing — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agents Shipgate Agent-Native Protocol

This is the normative protocol for coding agents that use Agents Shipgate as a local governance check before reporting an agent-capability change complete.

Agents only need one command and one JSON schema:

shipgate check --agent codex --workspace . --format agent-boundary-json

Use --agent claude-code for Claude Code and --agent cursor for Cursor. This value identifies the calling agent and changes only actor/rerun metadata; it never selects or disables host coverage. Every recognized changed boundary surface is evaluated on every invocation. The command writes no repo artifacts by default. It prints one JSON object to stdout: shipgate.agent_boundary_result/v2.

agents-shipgate verify and agents-shipgate-reports/report.json remain the full CI and reviewer substrate. Coding agents should use them for committed PR verification and reviewer evidence, but their local control loop is shipgate check plus shipgate.agent_boundary_result/v2.

Command

Default local check:

shipgate check --agent codex --workspace . --format agent-boundary-json

Committed diff check:

shipgate check --agent codex --workspace . --base origin/main --head HEAD --format agent-boundary-json

Fixture or MCP-provided diff:

shipgate check --agent codex --workspace . --diff change.diff --format agent-boundary-json
shipgate check --agent codex --workspace . --diff - --format agent-boundary-json

A supplied file or stdin diff is detached diagnostic input: it is not bound to checkout bytes that verify can reconstruct. Shipgate can still report boundary findings from it, but when the result owes verification it returns human_review_required with no allowed command. Re-run the check against the intended worktree, or with both --base and --head, to obtain a replayable verification route.

The no---diff form resolves a git diff locally. With no --base or --head, it reads local staged, unstaged, deleted, renamed, and relevant untracked changes. With --base and --head, it reads base...head. Supplying only one of --base or --head is invalid; omit both for local work or provide both for committed refs. Shipgate never fetches refs.

Read the full file on GitHub · 379 lines

Changes

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.

  1. yesterday First seen · 379 lines · 0 tokens per session scan A 510f9b2c165c

Subscribe to this mod's changes

protocol is an agent published in the GitHub repository ThreeMoonsLab/agents-shipgate (87 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,818 tokens. 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.

Related

Other agents, from other repositories

ci-cd-engineer

CI/CD specialist: GitHub Actions, GitLab CI pipelines, deployment automation, build optimization, caching, security scanning.

yonatangross/orchestkit · 30 tokens

test-runner

Runs tests in the api-gateway Maven reactor — full/module unit runs, isolating a single core test class, or a single distribution/tutorial example test. Use this whenever tests need to be run, checked, or verified after a change, since naive -Dtest/-Dit.test invocations silently run (or skip) the wrong thing in this…

membrane/api-gateway · 82 tokens

issue-feature-review

Review GitHub feature requests with constructive skepticism. Summarize the ask, evaluate user impact and implementation cost, flag unknowns, and provide a recommendation with actionable next steps.

rjmurillo/ai-agents · 39 tokens

roadmap

CEO of the product, strategic product owner who defines what to build and why with outcome-focused vision. Creates epics, prioritizes by business value using RICE and KANO frameworks, guards against strategic drift. Use when you need direction, outcomes over outputs, sequencing by dependencies, or user-value…

rjmurillo/ai-agents · 64 tokens

code-reviewer

You are a specialized code review subagent for Visor. Your role is to perform deep, comprehensive code reviews with a focus on.

probelabs/visor · 0 tokens

a11y-write-playwright-tests

Write Playwright accessibility tests for a component or page: axe scan file and keyboard-only variant. Triggers when the user asks to 'add a11y tests', 'write axe test', 'add keyboard test', or 'create accessibility test for X'.

AmadeusITGroup/otter · 59 tokens