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 stop-and-savegit 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/stop-and-save)<a href="https://agentmods.dev/skills/nikolamin/claude-coordinator-kit/stop-and-save"><img src="https://agentmods.dev/badge/skills/nikolamin/claude-coordinator-kit/stop-and-save/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/nikolamin/claude-coordinator-kit/stop-and-save"><img src="https://agentmods.dev/badge/skills/nikolamin/claude-coordinator-kit/stop-and-save.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 | $0.00230 | $0.01168 |
| Opus 5 | $0.00115 | $0.00584 |
| Sonnet 5 | $0.00046 | $0.00234 |
| Haiku 4.5 | $0.00023 | $0.00117 |
Grade A, and why
stop-and-save 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 9d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stop and save
This skill packages the stop half of CLAUDE.md's Session stop / resume protocol for delivery via
a plugin — everything a session does the moment the founder says "stop and save your step" (or a
close variant), so a later session (this one resumed, or a fresh one) can pick the work back up
without losing anything. The companion resume half — "bootstrap yourself" reading what this skill
wrote — is coordinator-kit:bootstrap, not this skill.
1. Suspend dispatch
Stop dispatching anything new. Record the instruction verbatim and dated in STATE.md's Durable
decisions, in the "Autonomous dispatch suspended" slot. That rule's semantics — what stays running
while suspended (status reporting, the question queue, scheduled/checkpoint reports), what stops
(new agent/build/investigation dispatch), and that only an explicit founder instruction lifts it —
are already defined in the installed CLAUDE.md's Execute loop stop conditions and in
coordinator-kit:execute-loop's Suspension of autonomous dispatch section; point at those rather
than restating them here.
2. Close out every in-flight agent
For each agent currently dispatched, check its actual status:
- Finished → close it out normally into
STATE.md's Agent log, same as any other completed task (build, verify result, commit hash, disclosed caveats). - Still running → record it in
STATE.md's Current section using the in-flight schemacoordinator-kit:watchdogsdefines, so a fresh session can tell "still genuinely running" from "abandoned when the session ended" instead of guessing.
3. Write the stop note
Write a stop note at the top of STATE.md's Current section, marked so it is unmissable on
resume (e.g. a heading like ### STOP NOTE — <date> directly under the section header). It must
carry all six of the following — this is the complete list, not a starting point:
- Uncommitted work, per repo: the files, and what each one should become — not just what changed. An agent killed mid-task can leave a file holding either a real fix or a half-applied change, and only the stated intent distinguishes the two; without it, a resumed session cannot tell which one it's looking at.
- Repo state, per repo: HEAD commit, and whether it's pushed to origin.
- Outstanding founder decisions, numbered. For any pending question, its literal text — the
one-line context, the coordinator's own reasoning, the 2-4 options with their trade-offs and
recommendation, and the safe default — per
coordinator-kit:question-protocol's four required parts, copied verbatim, not paraphrased, so the resumed session re-asks it unchanged instead of reconstructing it from memory. - Resume actions, in the order they should happen.
- What landed this session — so a resumed session doesn't have to re-derive it from
git log. - Session lessons worth keeping — a correction, a gotcha, anything learned that isn't already a durable rule, so a hard-won lesson doesn't die with the session along with everything else that wasn't written down.
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.
- 9d ago First seen · 79 lines · 230 tokens per session scan A 3d6b7733a501
stop-and-save is a skill published in the GitHub repository nikolamin/claude-coordinator-kit (2 stars, last pushed 6d ago), licensed MIT. It adds 230 tokens to every session and 1,168 once invoked, about $0.0011 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…