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 kirill-sviridov/handoff-mcp --skill planninggit clone --depth 1 https://github.com/kirill-sviridov/handoff-mcpWrote 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/kirill-sviridov/handoff-mcp/planning)<a href="https://agentmods.dev/skills/kirill-sviridov/handoff-mcp/planning"><img src="https://agentmods.dev/badge/skills/kirill-sviridov/handoff-mcp/planning/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/kirill-sviridov/handoff-mcp/planning"><img src="https://agentmods.dev/badge/skills/kirill-sviridov/handoff-mcp/planning.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 | $0.00135 | $0.00744 |
| Opus 5 | $0.00068 | $0.00372 |
| Sonnet 5 | $0.00027 | $0.00149 |
| Haiku 4.5 | $0.00014 | $0.00074 |
Grade A, and why
session-planning 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 12d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session-sized planning with handoff-mcp
Turn a big task into an ordered list of chunks, each small enough to finish (or make real progress on) in one focused working session, and store the plan in memory so it survives across sessions.
This skill only uses the existing handoff-mcp tools — it adds no new ones. If the server isn't connected, you can still produce the plan, but warn the user it won't persist between sessions.
1. Scope it (briefly)
Ask at most one or two clarifying questions if the goal is genuinely ambiguous (target, constraints, what "done" means). Don't over-interrogate — prefer sensible assumptions and state them.
2. Decompose into session-sized chunks
Break the work into an ordered list of milestones. Each chunk should be:
- a coherent, independently completable piece (something you could checkpoint),
- roughly one focused session of work,
- phrased as an outcome ("Auth flow works end-to-end"), not a vague theme.
Front-load the riskiest/most-uncertain chunks so dead-ends surface early.
3. Estimate honestly
Give a rough session count, explicitly labelled as a guess — e.g. "≈4–6 sessions, depends on X". Do not present a precise number as fact; LLMs estimate effort poorly. The real signal is progress against the chunk list, not the original guess.
4. Persist the plan in memory
- Save the plan as a durable entity:
note_entity("Plan", "<ordered chunks>")(or a project-specific name). Reference it as[[Plan]]. - Record the overall goal:
log_event(type="goal", ...). - Set the first chunk as the immediate next action:
log_event(type="next_step", "Chunk 1: …").
5. Work the plan, one chunk per session
- Start each session with
get_brief(the session-handoff skill covers this) to see the goal, current chunk, and what's done. - When a chunk is finished, record it:
log_event(type="decision"/"next_step", …)and append progress to the plan:note_entity("Plan", "DONE: chunk N — …"). Set the next chunk as the newnext_step. - At the end of the session,
checkpointso the next session resumes mid-plan.
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.
- 12d ago First seen · 68 lines · 135 tokens per session scan A 91d53629b336
session-planning is a skill published in the GitHub repository kirill-sviridov/handoff-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 135 tokens to every session and 744 once invoked, about $0.0007 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…