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-connect-repogit 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-connect-repo)<a href="https://agentmods.dev/skills/hivemind-oss/hivemind/hive-connect-repo"><img src="https://agentmods.dev/badge/skills/hivemind-oss/hivemind/hive-connect-repo/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-connect-repo"><img src="https://agentmods.dev/badge/skills/hivemind-oss/hivemind/hive-connect-repo.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 | $0.00150 | $0.04211 |
| Opus 5 | $0.00075 | $0.02106 |
| Sonnet 5 | $0.00030 | $0.00842 |
| Haiku 4.5 | $0.00015 | $0.00421 |
Grade A, and why
hive-connect-repo scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hive-connect-repo — register a repo & test the census feed
Register git repos with a running server so the sync daemon feeds tracked-branch landings into the change-outcome ledger — and judges anchor drift — automatically, per repo. One store, partitioned by repo: register each repo the fleet works in. This skill does not connect agents/teammates (that is hive-connect-team) or tune the sync loop's knobs (that is hive-operate).
The whole connection is outbound git-over-HTTPS with the token resolved from an env var —
no gh CLI, no GitHub App, no SSH key, and nothing installed in the consuming repo (census
and drift are server-side; agents are thin, repo-agnostic MCP clients). The server reaches out
to the remote; nothing inbound is required for the feed.
CLI resolve (once per shell): command -v hive >/dev/null 2>&1 || hive() { python3 -m hive.tools.cli "$@"; }
— 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).
1. Preflight — server up
hive status # or hive_health() over MCP — confirm the server is ok
If it is down, bring it up first (hive-bringup).
2. Gather inputs (walk through anything missing)
- Repo URL — the
https://…/ORG/REPO.gitform. An SSH URL ([email protected]:…) will not authenticate; no key is provisioned. HTTPS only. A public repo needs no token (the fetch runs anonymous). - Token — only for a private remote. Mint a least-privilege, read-only GitHub token:
Settings → Developer settings → Personal access tokens → Fine-grained → grant the repo
Repository permissions → Contents: Read-only. A classic PAT with
reposcope or a machine-user / App-installation token work too — the daemon uses the git transport, not the GitHub API. Put the value in an env var in the server's.env; the registry gets only the var's NAME (--token-env). Unset, the daemon falls to the fleet-defaultHIVE_SYNC__TOKENat tick time; that too absent ⇒ anonymous. - Branch — optional. Unset, the daemon tracks the remote's origin default branch. Pass
--branch <ref>only to pin a different tracked line.
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.
- 12d ago First seen · 245 lines · 150 tokens per session scan A de441921adde
hive-connect-repo is a skill published in the GitHub repository Hivemind-OSS/Hivemind (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 150 tokens to every session and 4,211 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-multi-repo
Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration.
Hooks Automation
Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre/post task hooks, session management, Git integration, memory coordination, and neural pattern training for enhanced development workflows.
meeting-todos
Use when the user says /meeting-todos, "the meeting is done", "I just had a meeting", "pull the action items", "what did I commit to", or otherwise wants action items from a recent meeting note captured on their to-do list. Also when a meeting note or transcript needs its tasks pulled out. NOT for general task…
instinct-import
Use when bringing a teammate's, another machine's, or another harness's instincts into this vault: the user runs /instinct-import, shares a portable YAML instinct pack (PACK.yaml), or asks to merge, adopt, sync, or inherit shared instincts. Confidence-gated so local instincts are never clobbered. Part of the Instinct…
secret-warn
Use when adding or tuning edit-time secret and code-injection guardrails or security hooks in Claude Code, or on mentions of secret detection, API key safety, hardcoded or leaked keys (AWS, Stripe, GCP, OpenAI, Anthropic, GitHub, Slack, JWT, PEM, .env), gitleaks-style or pre-commit secret scanning, false positives or…
ship
Release-gate sequence: validate → review → push → tag. Wraps kernel:git mechanics with the pre-ship safety chain. Triggers: ship, release, push to main, ready to merge, deploy.