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-engineering-consolidation-guardgit 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-engineering-consolidation-guard)<a href="https://agentmods.dev/skills/cratis/ai/cratis-engineering-consolidation-guard"><img src="https://agentmods.dev/badge/skills/cratis/ai/cratis-engineering-consolidation-guard/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-engineering-consolidation-guard"><img src="https://agentmods.dev/badge/skills/cratis/ai/cratis-engineering-consolidation-guard.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 | $0.00139 | $0.02351 |
| Opus 5.5 | $0.00056 | $0.00940 |
| Sonnet 5.5 | $0.00028 | $0.00470 |
| Haiku 4.5 | $0.00014 | $0.00235 |
Grade A, and why
cratis-engineering-consolidation-guard 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.
How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Consolidations and re-lands prove nothing was dropped
A consolidation is any branch whose job is to carry changes authored somewhere else: several pull requests folded into one, reverted work brought back, commits restored from an abandoned branch. Its sources are those original branches and commits.
The combined tree is built and specified before it merges, and that is exactly why loss goes unnoticed. A change deleted by the merge itself leaves nothing behind to fail: a deleted specification cannot go red, and a file a conflict resolution put back to its old content compiles fine. The guard compares the result with every source, path by path, and turns each loss into a finding.
A re-land is a consolidation. Work that landed, was reverted and is landed again has one source, the original change, and loses files the same way. Run the same guard against that original change, not against the revert.
When the guard applies
- Folding two or more pull requests onto one branch, as pull-requests.md asks for small related work.
- Re-landing reverted work, whether by reverting the revert, cherry-picking the original commits, or merging the original branch again.
- Restoring commits by cherry-pick: from a deleted branch, a closed pull request, or a backport.
- Reviewing any of the above before it merges.
It does not apply to merging the base branch into a feature branch (the base is not a source), or to a fresh implementation that shares no history with the work it replaces; there, specify the behavior instead.
Consolidate without rewriting history
git-commits.md forbids rebase, squash and force. Each permitted way to consolidate also records its source in history, which is what lets CI find the sources without being told:
| Situation | Default | Recorded as |
|---|---|---|
| Fold a pull request | git merge --no-ff pr631 |
a merge whose second parent is the folded tip |
| Restore commits | git cherry-pick -x <sha> |
a (cherry picked from commit <sha>) line |
| Re-land reverted work | git revert <revert-sha> |
This reverts commit <revert-sha>. |
What ships with it
3 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.
- 2d ago First seen · 198 lines · 139 tokens per session scan A 3423f599d370
cratis-engineering-consolidation-guard is a skill published in the GitHub repository Cratis/AI (4 stars, last pushed yesterday), licensed MIT. It adds 139 tokens to every session and 2,351 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 2026-10-19.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…