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 agents/threemoonslab/agents-shipgate/claude-codegit clone --depth 1 https://github.com/ThreeMoonsLab/agents-shipgateWhat 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 | $0.00000 | $0.00451 |
| Opus 5 | $0.00000 | $0.00226 |
| Sonnet 5 | $0.00000 | $0.00090 |
| Haiku 4.5 | $0.00000 | $0.00045 |
Grade A, and why
claude-code 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 2d 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.
What it actually says
Use Agents Shipgate With Claude Code
Claude Code uses the shared agent-native protocol:
shipgate check --agent claude-code --workspace . --format agent-boundary-json
Parse stdout as shipgate.agent_boundary_result/v2. Switch only on
control.state; follow control.next_action, control.allowed_next_commands,
and control.human_review. Treat decision as diagnostic context only.
--agent claude-code labels the caller; it does not limit the check to Claude
files or hide changes to another host's boundary.
If the binary is missing, surface the schema-valid install fixture with
control.state="agent_action_required", control.next_action.kind="install",
and command pipx install agents-shipgate.
After installation, rerun shipgate check; do not invent a natural-language
decision.
Claude Code-specific discovery surfaces:
.claude/settings.jsonand.claude/settings.local.jsonpermission modes, rules, sandbox/network settings, additional paths, plugins, and hooks- project MCP declarations in
.mcp.json - repo-level
CLAUDE.md - repo-scoped skill
.claude/skills/agents-shipgate/ - slash command
/agents-shipgatewhen the skill is installed
Use shipgate audit --host --scope local-static only when you intentionally
want supported user and file-based managed settings included. Shipgate never
executes policyHelper and does not observe remote/session state.
For committed PR verification, use the CI substrate after the local check:
agents-shipgate verify --workspace . --config shipgate.yaml --base origin/main --head HEAD --ci-mode advisory --format json
Read agents-shipgate-reports/agent-handoff.json first, then
verifier.json, then verify-run.json, then report.json for reviewer
evidence. Legacy agent-result.json surfaces are supporting/provisional
compatibility projections for older automation consumers.
See protocol.md for the state machine, repair loop, policy discovery convention, and MCP read-only boundary.
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.
- 2d ago First seen · 47 lines · 0 tokens per session scan A 47487168ed80
claude-code is an agent published in the GitHub repository ThreeMoonsLab/agents-shipgate (87 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 451 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.
Other agents, from other repositories
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
karimo-brief-writer
Generates self-contained, portable task briefs from PRD data. Spawned by /karimo:run Phase 1 for each task.
karimo-implementer-opus
Executes complex coding tasks (complexity 5+) from KARIMO PRDs. Writes production code with deep reasoning, multi-file coordination. Use for high-complexity implementation, refactoring, and architectural changes.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
INDEX
Agent "INDEX" from blueflyio/openstandardagents, covering production-ready ossa examples - complete index, directory structure, files by category, ossa manifests (10 files - all validated ✅) and openapi specifications (10 files - all complete ✅).
SUMMARY
This directory contains 10 complete, production-ready agent examples built with OSSA v0.3.6. Each example demonstrates real-world use cases with full implementations including OSSA manifests, OpenAPI specs, Docker deployments, and working exports.