Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/zkysar1/claude-mind/boot)<a href="https://agentmods.dev/skills/zkysar1/claude-mind/boot"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/boot.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 | $0.00086 | $0.09492 |
| Opus 5 | $0.00043 | $0.04746 |
| Sonnet 5 | $0.00017 | $0.01898 |
| Haiku 4.5 | $0.00009 | $0.00949 |
Grade A, and why
boot 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 6d 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 — 841 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/boot — Session Entry Point & Status Report
Read core/config/status-output.md for status line formats (session boundary, goal start, etc.).
The single entry point for each session. Resolves pending hypotheses (catch-up), generates a comprehensive status report, then hands off to /aspirations loop for perpetual execution. Auto-invoked by /start or during inline restart. Requires RUNNING agent-state.
Key design: Boot calls /review-hypotheses --resolve (detect outcomes) but does NOT trigger learning. Learning happens downstream when /aspirations loop picks up goals that call /review-hypotheses --learn.
Step 0: Load Conventions — Bash: load-conventions.sh with each name from the conventions: front matter. Read only the paths returned (files not yet in context). If output is empty, all conventions already loaded — proceed to next step.
Phase -3: Agent State Gate Check
Bash: session-state-get.sh → read output.
IF output is "UNINITIALIZED" → ABORT: "Agent not initialized. User must run /start." IF output is "IDLE" → ABORT: "Agent is stopped. User must run /start to resume." IF output is "RUNNING" → PROCEED.
This gate means boot can ONLY run when /start has set agent-state to RUNNING.
Phase -2.5: Crash Recovery Detection
Check for crash marker left by StopFailure hook (context exhaustion in previous session):
IF file exists agents/<agent>/session/crash-marker:
Read content (format: "<timestamp> context_exhaustion sid=<session-id>")
Log: "⚠ Previous session ended abnormally — context exhaustion detected"
Log the crash-marker content for diagnostics
Delete agents/<agent>/session/crash-marker
Phase -2: State Initialization (First Boot)
Run the deterministic init scripts. They create world/ (collective state), / (per-agent state),
and meta/ (meta-strategies) from core/config/ initial_state: sections.
Idempotent — each exits immediately if its .initialized marker already exists.
Run: bash core/scripts/init-mind.sh $MIND_AGENT
IF exit code != 0: ABORT with error message
IF output contains "First boot": log "First boot detected — agent is a blank slate"
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.
- 6d ago First seen · 841 lines · 86 tokens per session scan A 97d957306569
boot is a skill published in the GitHub repository zkysar1/Claude-Mind (5 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 9,492 once invoked, about $0.0004 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
cron-management
Skill for reading and writing cron.md in the correct format for scheduled LLM or command tasks. Use when: editing cron.md, adding or changing cron schedules, or removing periodic jobs.
zoom-meeting-scribe
Listen-only scribe workflow for Zoom meetings. Silently understand and record meeting transcripts delivered via RTMS, escalate only urgent matters to your supervisor, and post the report only after human approval once the meeting ends. Use when: receiving an inbox message with source=zoom (carrying a "[Zoom会議実況 チャンク#N…
chatwork-tool
Chatwork integration tool for send/receive messages, search, unreplied checks, and room listing. Use when: posting to Chatwork, listing rooms, checking unreplied threads, searching messages, or handling mentions.
discord-tool
Discord integration tool for messaging, search, guild and channel listing, and reactions. Use when: posting to Discord, listing channels, searching messages, or adding reactions in guilds.
notion-tool
Notion integration tool for searching, reading, creating, and updating pages and databases via the API. Use when: editing Notion pages, adding database rows, or searching a workspace.
slack-tool
Slack integration tool for send/receive messages, search, unreplied checks, channel listing, and emoji reactions. Use when: posting to Slack, listing channels, replying in threads, checking unreplied items, or adding reactions.