Borrowing it
Nothing to install: this file belongs to zkysar1/Claude-Mind. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zkysar1/Claude-Mind/main/.claude/skills/start/SKILL.mdgit clone --depth 1 https://github.com/zkysar1/Claude-MindWrote 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/start)<a href="https://agentmods.dev/skills/zkysar1/claude-mind/start"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/start.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 | $0.00141 | $0.16356 |
| Opus 5 | $0.00071 | $0.08178 |
| Sonnet 5 | $0.00028 | $0.03271 |
| Haiku 4.5 | $0.00014 | $0.01636 |
Grade A, and why
start 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.
How it starts
The opening of the file, as written. The whole thing — 915 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/start — Start or Resume Agent
USER-ONLY COMMAND. Claude must NEVER invoke this skill.
Syntax
/start <agent-name> # Default: autonomous (backward compat)
/start <agent-name> --mode reader # Read-only knowledge access
/start <agent-name> --mode assistant # User-directed learning
/start <agent-name> --mode autonomous # Full perpetual loop (same as no flag)
/start <agent-name> --reducer-only # Refuse the automatic second-body join on rc=4
Rationale: core/config/rationale/start-preflight-and-recovery.md — The body role is DERIVED, not declared (user direc
On resume (agent already exists):
/start # Resume in current mode
/start --mode <mode> # Switch mode and resume
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.
Step 0.5: Parse Mode + Recovery Flags — Extract the following from positional arguments:
The flag parser must run flag extraction BEFORE positional extraction so /start --recover (no agent name) binds to the current session's agent rather than being misinterpreted as /start <agent-name=--recover>.
Step 0.6: Output-style preflight (autonomous mode only) — When the parsed mode is autonomous (the default), read .claude/settings.local.json for the active outputStyle and warn the user IMMEDIATELY if it's set to Explanatory. The C7.7 Layer-B gate fires the same check later, but only AFTER all the long Phase A/B/C work (path prompts, permissions, init-mind, conventions, The Program, identity). Failing at C7.7 wastes ~30+ min of user investment. This preflight surfaces the collision before any state mutation.
Bash: $(command -v py >/dev/null && echo "py -3" || echo python3) -c "import json,pathlib;p=pathlib.Path('.claude/settings.local.json');s=(json.loads(p.read_text(encoding='utf-8')).get('outputStyle') or '').strip().lower() if p.exists() else '';print(s)" 2>/dev/null
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 3799d4ccc429
- 6d ago First seen · 910 lines · 141 tokens per session scan A 7320602746dc
start is a skill published in the GitHub repository zkysar1/Claude-Mind (5 stars, last pushed today), licensed MIT. It adds 141 tokens to every session and 16,356 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
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.worker-delegation
Concrete patterns for breaking colony work into parallel worker jobs via runplaybook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence retry/resume the gap.
hive.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…
hive.x-automation
Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
hive.writing-hive-skills
Author a new Agent Skill for a Hive agent that conforms to the Agent Skills specification (SKILL.md with YAML frontmatter, optional scripts/references/assets directories). Use when the user asks to create, scaffold, add, or package a new skill for a Hive agent.