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 Hivemind-OSS/Hivemind --skill hive-operategit clone --depth 1 https://github.com/Hivemind-OSS/HivemindWrote 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/hivemind-oss/hivemind/hive-operate)<a href="https://agentmods.dev/skills/hivemind-oss/hivemind/hive-operate"><img src="https://agentmods.dev/badge/skills/hivemind-oss/hivemind/hive-operate/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/hivemind-oss/hivemind/hive-operate"><img src="https://agentmods.dev/badge/skills/hivemind-oss/hivemind/hive-operate.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 | $0.00149 | $0.02803 |
| Opus 5 | $0.00075 | $0.01401 |
| Sonnet 5 | $0.00030 | $0.00561 |
| Haiku 4.5 | $0.00015 | $0.00280 |
Grade A, and why
hive-operate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hive-operate — watch the KPIs & turn the knobs
Keep a running server lean and current. The store does not clean itself — maintenance is the
product. Full leverage map: OPERATIONS.md; knob tables: HIVE-ADMIN.md §4 & §6.
CLI resolve (once per shell): command -v hive >/dev/null 2>&1 || hive() { python3 -m hive.tools.cli "$@"; }
— makes every hive … line below run on an uninstalled checkout (the CLI is stdlib-only;
Windows shells: py -m hive.tools.cli <verb>; prerequisites: hive-bringup).
For a browser view of the live picture, hive ui serves a loopback-only operator dashboard (live
status, seat mint/revoke, backup, non-blocking start/stop, tunnel activate/deactivate, restore from
an in-volume backup behind a typed confirm, log tail; no reset) — --no-open for a headless host.
The KPIs below stay MCP-only; the dashboard is the docker-side status/lifecycle surface.
The KPIs — read-only over MCP, off the warm store
Call these from any connected agent (there is no host-side verb):
| Call | Tells you | Act on |
|---|---|---|
hive_health(include_trends=true) |
confident_rate + demand_entropy, current vs prior 7d + deltas |
tau_serve, demand_m |
hive_health(include_gaps=true) |
topics wanted but uncovered (misses carry their repo scope) | hive_write the answers |
hive_health(include_conflicts=true) |
near-duplicate / contradicting memories + agent advisories, bucketed by repo and anchor; established rows with rivals rank above provisional | hive_supersede the wrong one |
hive_health(include_suspect_consensus=true) |
promotions on thin effective independence | re-examine; retire via hive_supersede / hive_prune |
hive_health(include_stale_suspects=true) |
servable memories whose anchor sat in the blast radius of a breaking/removed change | re-verify each against the code; retire the truly stale |
hive_health(include_census_health=true) |
repos — per registered repo: days since the last change_outcome + the sync block (tracked_ref/last_tip/last_sync_ts/last_error/backfilled_total; status: "no change_outcome evidence yet" when configured yet dark — a measured fact about EVIDENCE, never a daemon verdict). fleet — the daemon's own last_sync_ts/last_error |
read fleet FIRST: a last_error there (or a frozen last_sync_ts) means the daemon is down and every repo block is a stale snapshot that still reads as passing → hive logs. Otherwise check the registry (hive repos), the token env var, remote reachability |
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.
- 8d ago First seen · 150 lines · 149 tokens per session scan A 53d22a6ad33b
hive-operate is a skill published in the GitHub repository Hivemind-OSS/Hivemind (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 149 tokens to every session and 2,803 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
github-code-review
Comprehensive GitHub code review with AI-powered swarm coordination.
Pair Programming
AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with…
V3 CLI Modernization
CLI modernization and hooks system enhancement for claude-flow v3. Implements interactive prompts, command decomposition, enhanced hooks integration, and intelligent workflow automation.
github-multi-repo
Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration.
Skill Builder
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build custom skills for specific workflows, generate skill templates, or understand the Claude Skills specification.
V3 Core Implementation
Core module implementation for claude-flow v3. Implements DDD domains, clean architecture patterns, dependency injection, and modular TypeScript codebase with comprehensive testing.