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/worker-loopnpx skills add zkysar1/Claude-Mind --skill worker-loopgit 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/worker-loop)<a href="https://agentmods.dev/skills/zkysar1/claude-mind/worker-loop"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/worker-loop.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 | $0.00126 | $0.20777 |
| Opus 5 | $0.00063 | $0.10389 |
| Sonnet 5 | $0.00025 | $0.04155 |
| Haiku 4.5 | $0.00013 | $0.02078 |
Grade A, and why
worker-loop 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 yesterday.
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 — 1,130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/worker-loop — Worker-Body Simplified Execution Loop (Phase 2A)
A worker Body is a forked instance of a Mind (keyed by unitKey = its
session SID) that is NOT the reducer. It runs a deliberately thin loop —
select -> claim -> execute -> re-enter — one work unit per pass, parking
(resumable, hourly re-poll) when work or its reducer is gone, leaving its
divergent working-memory for the single reducer to merge later. It does NOT verify,
encode, reflect, update state, run the learning gate, evolve, or do completion
review. Those are reducer-only: the one Body holding running-session-id
(the reducer) applies them to the MERGED state of every Body at generalize-down
(Phase 1C body-merge.py, run from aspirations-consolidate Step -1). Running
encode/reflect per-worker would create N reducers — the defect the convergence
forbids.
Activation status (updated 2026-08-05, fresh-eyes review): ACTIVATION IS
LANDED — g-306-119-a (/start worker auto-join branch), g-306-119-b (close-body
staging+push), g-306-119-c (baseline-aware merge consume) and g-306-125
(safety rails) are all completed, and a live worker executed a real goal via
this loop (g-315-518 soak, DESKTOP-O91DLK2). The prior "until Phase 2C wires
fork-activation" wording predated those landings. Still OPEN before trusting
multi-body at scale: g-306-120 (cross-box activation dry-run), g-306-126
(live two-box soak), g-306-128 (kill-tests), and g-306-131 (three fail-safe
inversions in the reducer-liveness poll this loop runs every cycle). Design
SSOT: the mind-engine-identity-bridge tree node (Phase 2).
The phase split (authoritative: worker_execute.py)
The phase contract is owned by core/scripts/worker_execute.py, NOT duplicated
here, so the worker and its tests agree on one source of truth:
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.
- yesterday Changed · -4 lines 3b027616b893
- 4d ago First seen · 1,134 lines · 126 tokens per session scan A 1d553c8d168d
worker-loop is a skill published in the GitHub repository zkysar1/Claude-Mind (5 stars, last pushed yesterday), licensed MIT. It adds 126 tokens to every session and 20,777 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.