Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Hivemind-OSS/Hivemindnpx agentmods add skills/hivemind-oss/hivemind/hive-upgradeWrote 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-upgrade)<a href="https://agentmods.dev/skills/hivemind-oss/hivemind/hive-upgrade"><img src="https://agentmods.dev/badge/skills/hivemind-oss/hivemind/hive-upgrade/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-upgrade"><img src="https://agentmods.dev/badge/skills/hivemind-oss/hivemind/hive-upgrade.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 | $0.00131 | $0.02707 |
| Opus 5 | $0.00066 | $0.01354 |
| Sonnet 5 | $0.00026 | $0.00541 |
| Haiku 4.5 | $0.00013 | $0.00271 |
Grade A, and why
hive-upgrade scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hive-upgrade — move to a release ref without losing the store
hive upgrade moves the server's checkout to a different git ref and rebuilds it. That is
different from hive up (which rebuilds whatever is already checked out) and from hive restore
(which replaces store contents, not code). Lifecycle basics: hive-bringup. Snapshots and
recovery: hive-backup-restore. Full reference: HIVE-ADMIN.md §8.
CLI resolve (once per shell): command -v hive >/dev/null 2>&1 || hive() { python3 -m hive.tools.cli "$@"; }
— makes every hive … line below run on an uninstalled checkout (the CLI is stdlib-only;
Windows shells: py -m hive.tools.cli <verb>).
The one thing that can actually cost you data
This build has no in-place store migration. SqliteEpisodeStore.__init__ refuses to open a
store whose shape does not match the code, on purpose — a CREATE IF NOT EXISTS would leave an
old table in place and limp to a cryptic mid-query crash. The refusal surfaces as a boot exit
70 and a crash-loop, with store.schema_pre_v3 (or store.schema_predates_v3 /
store.schema_missing_episode_anchors) in the logs.
So a schema-breaking release is never a routine update — it is a decision about whether to keep
the corpus. hive upgrade protects the data automatically; it cannot make an incompatible ref
adoptable.
hive up after a manual git checkout is the dangerous path — no snapshot gate, no health
gate, no rollback. If the new ref refuses the store you get a crash-loop against a store nothing
snapshotted. Always move refs with hive upgrade.
1. Pre-flight — will the target ref accept this store?
Run this before anything else. It reads the target ref via git show + ast (never imported,
never executed) and the live store mode=ro, then compares them against the three assertions the
target's own boot makes:
python3 skills/hive-upgrade/preflight.py release # or any tag / branch / SHA
| Verdict | Exit | What it means | Do |
|---|---|---|---|
PASS |
0 | the target ref's schema contract accepts the live store | continue to step 2 |
SCHEMA BREAK |
1 | the target will refuse this store at boot; it names the exact columns/tables | stop — go to "when the pre-flight fails" |
UNKNOWN |
2 | the contract could not be read (ref predates these constants, or they were renamed) | stop and treat as a break — it is not proven safe |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 197 lines · 131 tokens per session scan A da5a2f88f880
hive-upgrade is a skill published in the GitHub repository Hivemind-OSS/Hivemind (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 131 tokens to every session and 2,707 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.
github-multi-repo
Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration.
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…
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 CLI Modernization
CLI modernization and hooks system enhancement for claude-flow v3. Implements interactive prompts, command decomposition, enhanced hooks integration, and intelligent workflow automation.
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.