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 agentmods add skills/zkysar1/claude-mind/stopnpx skills add zkysar1/Claude-Mind --skill stopgit 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/stop)<a href="https://agentmods.dev/skills/zkysar1/claude-mind/stop"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/stop.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 | $0.00122 | $0.05164 |
| Opus 5 | $0.00061 | $0.02582 |
| Sonnet 5 | $0.00024 | $0.01033 |
| Haiku 4.5 | $0.00012 | $0.00516 |
Grade A, and why
stop 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 — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/stop -- Stop the Autonomous Learning Loop
USER-ONLY COMMAND. Claude must NEVER invoke this skill.
Syntax
/stop <agent-name> # Stop the named agent + drop to assistant (reconciliation-ready)
/stop <agent-name> --reader # Stop the named agent + drop to reader (read-only, walking away)
Agent name is REQUIRED. A bare /stop (no positional argument) is refused with a
clear error and the list of available agent directories. This prevents the cross-session
"wrong-agent stop" failure mode where a session's .active-agent-<SID> binding has
been silently overwritten or cleared (e.g., NO_AGENT window, or another /start rebinding
the SID), leaving /stop no safe default. Requiring the explicit name also enables stops
from any terminal — a side benefit, not a workaround. (Incident: 2026-04-24 — bare /stop
typed in a NO_AGENT window stopped the wrong agent because the binding fell back to a
different active agent's session.)
After stop, the agent lands in assistant mode by default so the user can immediately
reconcile state (mark a missed goal, edit a tree node, add a guardrail) without a mode
switch. Pass --reader for the read-only safe floor when walking away.
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 arguments — flag-parsing runs before positional-parsing so /stop --reader (no agent-name) is not mis-interpreted as /stop <agent-name=--reader>.
-
Flag parsing: If any argument is the literal string
--reader, settarget_mode = "reader". Otherwisetarget_mode = "assistant". This determines where the agent lands after the stop completes. Unknown flags are ignored (user will see the default output and can re-try). -
Agent name resolution (REQUIRED): Take the first argument that does NOT start with
--as<agent-name>. The positional argument is mandatory — there is NO fallback to current session binding.
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 · +12 lines 07fa4555fa23
- 6d ago First seen · 299 lines · 122 tokens per session scan A bee0eb299ab9
stop is a skill published in the GitHub repository zkysar1/Claude-Mind (5 stars, last pushed today), licensed MIT. It adds 122 tokens to every session and 5,164 once invoked, about $0.0006 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.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.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.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.