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 nikolamin/claude-coordinator-kit --skill escalationgit clone --depth 1 https://github.com/nikolamin/claude-coordinator-kitWrote 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/nikolamin/claude-coordinator-kit/escalation)<a href="https://agentmods.dev/skills/nikolamin/claude-coordinator-kit/escalation"><img src="https://agentmods.dev/badge/skills/nikolamin/claude-coordinator-kit/escalation.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 5.1 | $0.00316 | $0.00860 |
| Opus 5 | $0.00158 | $0.00430 |
| Sonnet 5 | $0.00063 | $0.00172 |
| Haiku 4.5 | $0.00032 | $0.00086 |
Grade A, and why
escalation 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
Escalation
This skill packages CLAUDE.md's Escalation section for delivery via a plugin. If this
project's coordinator uses the file-copy install, the project-root CLAUDE.md already carries
this exact content under its own "Escalation" heading — this skill is a second, parallel
delivery path for the same rules, not a replacement.
- If an agent hits
coordinator-kit:execute-loop's retry cap on the same class of problem — 2 failed respawn cycles, escalating on the 3rd failure — or a design/architecture question has no clear path forward from normal iteration, spawn an agent with the advice tier (fable, perCLAUDE.md's Model routing section) for advice. Prompt: self-contained summary of what was tried and what's blocking, framed as "what would you try next." This is distinct from a routine respawn — don't reach for it on a first failure. - For UI/UX design decisions, copy/copywriting (marketing text, UX microcopy, landing-page
text), research tasks, and reviewing generated documents, additionally shell out to
codex exec(OpenAI Codex CLI, if installed and authenticated) from within a dispatched agent for a second, differently-trained opinion — seecoordinator-kit:codex-second-opinionfor install, auth, and invocation mechanics. Present its output alongside a Claude-native alternative when the choice is user-facing; adopt it outright for mechanical asks. Engineering-only work (wire types, plumbing, test scaffolding) doesn't need this — the trigger is judgment/perspective value, not mechanical execution. - An agent given unrestricted
Agent/SendMessageaccess can spiral into agent-to-agent delegation instead of doing the work. For any infra/execution task, the brief must include: "do not delegate, execute directly; bulk output (test suites, builds, big greps) goes to a scratch file under.coordinator-scratch/— paste only the decisive lines (failure names, exit codes, the mutation transcript)." A pasted suite log is re-read by that agent on every later step of its own turn (~29% of agent cost in a measured 48M-token session), and the coordinator gates on the decisive lines anyway.
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 Changed · +5 lines · +4 tokens per session 6d6dc0a23d7a
- 6d ago First seen · 45 lines · 312 tokens per session scan A 021e1525fd4d
escalation is a skill published in the GitHub repository nikolamin/claude-coordinator-kit (2 stars, last pushed 4d ago), licensed MIT. It adds 316 tokens to every session and 860 once invoked, about $0.0016 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.
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…
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…