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/moasq/agentic-ship/agent-compatibilitynpx skills add moasq/agentic-ship --skill agent-compatibilitygit clone --depth 1 https://github.com/moasq/agentic-shipWrote 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/moasq/agentic-ship/agent-compatibility)<a href="https://agentmods.dev/skills/moasq/agentic-ship/agent-compatibility"><img src="https://agentmods.dev/badge/skills/moasq/agentic-ship/agent-compatibility.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 | $0.00073 | $0.01552 |
| Opus 5 | $0.00036 | $0.00776 |
| Sonnet 5 | $0.00015 | $0.00310 |
| Haiku 4.5 | $0.00007 | $0.00155 |
Grade A, and why
agent-compatibility 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 today.
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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent compatibility
Preserve one authored system and generate only the host syntax needed to expose it. Treat a native adapter as delivery machinery, never as a second home for doctrine.
Keep the canonical layer singular
Use these sources as the authority:
| Concern | Canonical source |
|---|---|
| repository rules | AGENTS.md |
| procedures | .agents/skills/*/SKILL.md |
| dispatch roles | .agents/agents/*.md |
| MCP inventory | .mcp.json |
| product and handoff contracts | .agents/contracts/ |
Change the canonical source first. Regenerate an adapter after the source change.
Never repair drift by editing a generated Claude plugin, Codex, Cursor, Hermes, or OpenClaw file directly.
Never restate an AGENTS.md rule inside an adapter or skill.
Synchronize native adapters
Run the write pass after changing a canonical role or .mcp.json:
pnpm sync:agents
Run the read-only drift check after install and before completion:
pnpm check:agents
Run the MCP mirror check separately:
pnpm check:mcp
Treat any generated-file drift as a local configuration defect. Re-run the matching
sync command; do not copy content by hand. Run pnpm health afterward to check the
rest of the static workspace contract.
Use the native surface for each host
| Host | Rules and skills | Native roles | MCP and enforcement |
|---|---|---|---|
| Claude Code | CLAUDE.md imports AGENTS.md; .claude/skills resolves to .agents/skills |
.claude/agents resolves to canonical roles in-project; generated top-level agents/ ships the plugin roles |
.mcp.json; plugin wiring and the completion hook live in .claude/settings.json |
| Codex | reads AGENTS.md and project skills |
generated .codex/agents/*.toml |
generated project-scoped .codex/config.toml, including direct MCP URLs |
| Cursor | reads AGENTS.md and Agent Skills |
generated .cursor/agents/*.md |
generated .cursor/mcp.json; use native hooks when a checked adapter declares them |
| Hermes | reads AGENTS.md; .hermes/profile/config.yaml adds .agents/skills through skills.external_dirs |
.hermes/profile/SOUL.md and the generated role catalog drive delegate_task from canonical briefs |
generated profile entry for the local Agentic Ship server; configure OAuth MCP in the selected profile or user config and keep tokens outside the repository |
| OpenClaw | reads AGENTS.md and discovers .agents/skills natively with this repository as the agent workspace; .openclaw/config.json5 is the non-secret template for any other workspace |
generated .openclaw/roles.md drives sessions_spawn from canonical briefs |
generated template entry for the local Agentic Ship server; configure OAuth MCP with the host CLI in user configuration and keep tokens outside the repository |
What ships with it
2 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.
- today Changed · +1 lines 8e40f8822817
- 4d ago First seen · 131 lines · 73 tokens per session scan A d2021ae95f0d
agent-compatibility is a skill published in the GitHub repository moasq/agentic-ship (11 stars, last pushed 3d ago), licensed MIT. It adds 73 tokens to every session and 1,552 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…