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 kostya-pakhomov/graphmind --skill graphmind-planninggit clone --depth 1 https://github.com/kostya-pakhomov/graphmindWrote 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/kostya-pakhomov/graphmind/graphmind-planning)<a href="https://agentmods.dev/skills/kostya-pakhomov/graphmind/graphmind-planning"><img src="https://agentmods.dev/badge/skills/kostya-pakhomov/graphmind/graphmind-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/kostya-pakhomov/graphmind/graphmind-planning"><img src="https://agentmods.dev/badge/skills/kostya-pakhomov/graphmind/graphmind-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 | $0.00124 | $0.01283 |
| Opus 5.5 | $0.00050 | $0.00513 |
| Sonnet 5.5 | $0.00025 | $0.00257 |
| Haiku 4.5 | $0.00012 | $0.00128 |
Grade A, and why
graphmind-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 1mo 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GraphMind — планирование через иерархию P0/P1/P2/P3
Навык покрывает декомпозицию больших задач в дерево планов с явным жизненным циклом. Требуется подключённый MCP-сервер graphmind (см. README плагина, раздел «Подключение»). Планы живут между сессиями, как и память.
1. Когда использовать
- Задача размытая («улучшить UX», «подготовить релиз»).
- Задача > 3 логических шагов или > 1 сессии работы.
- Нужен явный трекинг: что в работе, что заблокировано, что сделано.
- Несколько подзадач могут идти параллельно (разные суб-агенты).
Не использовать для одношаговых задач — это лишний overhead. Их проще вести через record_action + propose_new_memory.
2. Иерархия планов
| Уровень | Назначение | Кто создаёт | Кто завершает |
|---|---|---|---|
| P0 | Проблема/цель верхнего уровня | Агент-инициатор (plan_create_p0) |
— (живёт, пока есть активные дети) |
| P1 | Подход/подплан (требует human review) | Агент-инициатор (plan_propose_p1) |
Человек (plan_approve_p1 / plan_reject_p1) |
| P2 | Декомпозиция внутри подхода | plan_decompose от P1-узла |
Дальнейшая декомпозиция или выполнение |
| P3 | Конкретное действие, исполняется суб-агентом | plan_decompose от P2 |
Суб-агент (plan_claim → plan_complete) |
Связь: P0 → P1 → P2 → P3. Декомпозиция идёт сверху вниз, выполнение — снизу вверх.
Важно про decompose: вызов plan_decompose от P1 возвращает P2, не P3. Чтобы получить исполняемые P3, нужен повторный plan_decompose от каждого P2. plan_claim принимает только P3 и вернёт CLAIM_FAILED для P2 — это проверяли на тесте P0-fac9c88c-….
3. Базовый сценарий
# 1. Зафиксировать проблему
plan_create_p0({ description: "Подготовить публичную раскатку плагина GraphMind" })
# 2. Предложить подходы на ревью
plan_propose_p1({ p0_id: "<id>", description: "Шаг 1: верифицировать make-public.sh" })
plan_propose_p1({ p0_id: "<id>", description: "Шаг 2: поднять GitHub-репо" })
plan_propose_p1({ p0_id: "<id>", description: "Шаг 3: smoke-тест установки" })
# 3. Дождаться human-апрува (или уточнить через plan_reject_p1 с причиной)
plan_approve_p1({ p1_id: "<id>" })
# 4. Декомпозировать одобренный P1 в P2/P3
plan_decompose({ node_id: "<p1_id>" })
# 5. Суб-агент забирает P3 в работу
plan_claim({ agent_id: "coder-1", p3_id: "<p3_id>" })
plan_complete({ p3_id: "<p3_id>", result: "сделал X, проверил Y" })
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.
- 1mo ago First seen · 85 lines · 124 tokens per session scan A 5b7308e1aa52
graphmind-planning is a skill published in the GitHub repository kostya-pakhomov/graphmind (2 stars, last pushed 3mo ago), licensed MIT. It adds 124 tokens to every session and 1,283 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
using-cortex-memory
Use when connected to a Cortex memory MCP server (tools named memorize, recall, recallabout, recalltimeline, listmemories, forget) — at session start, before asking the user for facts they may have shared before, after learning durable facts/preferences/decisions, when the user says "remember/recall/forget", or when…
mnema
Use the Mnema MCP server to give the AI long-term, searchable memory. Use it whenever the user shares durable facts, preferences, decisions, or context worth recalling in future sessions. Mnema stores memories in a vector database and recalls them with semantic + hybrid search, with decay scoring and summarization so…
ix
Answer structural questions about a codebase — what a symbol is, what calls it, what a change breaks, where the hotspots are — from a persistent code graph via the ix CLI, instead of grepping.
honcho-integration
Integrate Honcho memory into existing Python or TypeScript codebases. Use when adding Honcho SDK, setting up peers, configuring sessions, and accessing Honcho's representation.
mnemo-cortex
Installs and wires Mnemo Cortex (local-first persistent memory) into OpenClaw and other MCP-capable agents. Use for cross-session recall, decision history, or multi-agent shared memory.
honcho-setup
First-run setup and health check for Honcho memory in Cursor or Grok Bot. Use when the user asks to set up, connect, sign in to, or check the status of Honcho; when Honcho tool calls return authentication errors; or when the workspace metadata has no userpeer yet.