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 Cratis/AI --skill cratis-orchestration-merge-gatesgit clone --depth 1 https://github.com/Cratis/AIWrote 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/cratis/ai/cratis-orchestration-merge-gates)<a href="https://agentmods.dev/skills/cratis/ai/cratis-orchestration-merge-gates"><img src="https://agentmods.dev/badge/skills/cratis/ai/cratis-orchestration-merge-gates/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/cratis/ai/cratis-orchestration-merge-gates"><img src="https://agentmods.dev/badge/skills/cratis/ai/cratis-orchestration-merge-gates.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00159 | $0.01187 |
| Opus 5.5 | $0.00064 | $0.00475 |
| Sonnet 5.5 | $0.00032 | $0.00237 |
| Haiku 4.5 | $0.00016 | $0.00119 |
Grade A, and why
cratis-orchestration-merge-gates 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merge in turn, on evidence
This skill applies to multi-lane work where several pull requests merge into
one repository. A single session follows cratis-engineering-ci-gates.
Merging, like any external effect, needs the user's request or brief to
authorize it: read
capability-is-not-authority.md.
Placeholders such as <coordinator> and the default time boxes come from
cratis-orchestration-lanes and its
placeholders.md;
they are not redefined here.
Tier names
Lanes use short names for the gates already defined in
cratis-engineering-ci-gates. That skill owns the gate content; this table only
maps names.
| Lane term | Gate | When |
|---|---|---|
| Iteration | Affected checks | While editing, per lane |
| Ready to merge | Tier 1 on the assembled candidate | Before asking for a merge turn |
| Integration | Tier 2 or CI | On the pushed head, before merge |
A lane's own green iteration result is never ready-to-merge evidence for the assembled candidate.
Serial merge is decided by GitHub state
Merge turns are decided by GitHub state, never by a chat or inbox message saying "go". Merge only when all three hold, each read from GitHub or git just before the merge:
- Predecessors are merged. Every predecessor pull request the candidate
depends on is
MERGED, not merely approved or green. - No publish is running. No publish run of the repository is queued or in progress. A merge during a publish can race the release or be released under an unexpected version.
- No overlap since CI ran. Main has no changes touching the candidate's
paths since the commit its CI ran on:
git log <ci-sha>..origin/main -- <paths>prints nothing.
If any check fails, do not merge and do not wait in a loop: report which check
failed and the evidence, then hand the turn back to <coordinator>. Read
references/merge-queue.md for the gh api
commands and a worked example.
What ships with it
4 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 First seen · 101 lines · 159 tokens per session scan A 3f588e5a38da
cratis-orchestration-merge-gates is a skill published in the GitHub repository Cratis/AI (4 stars, last pushed today), licensed MIT. It adds 159 tokens to every session and 1,187 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-26.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…