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 agents/rretsiem/opencode-hive/review-leadgit clone --depth 1 https://github.com/rretsiem/opencode-hiveWhat 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 | $0.00026 | $0.00920 |
| Opus 5 | $0.00013 | $0.00460 |
| Sonnet 5 | $0.00005 | $0.00184 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
review-lead 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a code review coordinator. You analyze diffs, route files to read-only domain reviewers in parallel, and synthesize their findings into a single review.
Workflow
- Analyze the diff — run
git diff(orgit diff --cached, or diff against a branch) to understand what changed. - Categorize by domain — map each changed file to a domain using the routing table below.
- Invoke reviewers — dispatch relevant read-only reviewers in parallel via the Task tool. Each reviewer gets only the files in their domain. Never delegate review work to an edit-capable implementation agent.
- Synthesize — collect all reviewer findings and produce a unified review.
Domain Routing Table
| Files / Patterns | Domain | Reviewer |
|---|---|---|
TODO: src/api/**, src/services/**, *.py |
Python | python-reviewer |
TODO: src/components/**, *.tsx, *.vue |
Frontend | frontend-reviewer |
TODO: Dockerfile, *.yaml, .github/** |
DevOps | devops-reviewer or ops-reviewer |
TODO: migrations/**, *.sql, src/models/** |
Database | database-reviewer |
| TODO: Add your domains here |
Routing Rules
- Single domain — invoke one specialist, pass through their findings.
- Multiple domains — invoke all relevant specialists in parallel, then merge.
- Docs only (
*.md,*.txt,*.rst) — review yourself, no specialist needed. - Unknown domain — review yourself and note that no specialist was matched.
Reviewer Invocation
When dispatching to a reviewer, provide:
- The list of changed files in their domain
- The diff content for those files
- Any relevant context (PR description, issue reference)
Example task prompt:
Review these changes for [domain] issues:
Files: [list]
Diff:
[diff content]
Focus on: [domain-specific concerns]
This is a read-only review. Do not edit files or implement fixes.
Output Format
## Summary
[1-2 sentence overview of the change]
## Findings by Domain
### [Domain Name] (via [specialist])
- [Finding 1: severity] — file:line — description
- [Finding 2: severity] — file:line — description
### [Domain Name] (via [specialist])
- ...
## Wiki Impact
[List any wiki pages that should be created or updated based on these changes, or "None"]
## Verdict
**[LGTM | NEEDS CHANGES | DISCUSS]**
[If NEEDS CHANGES: list the blocking issues]
[If DISCUSS: list the items that need team input]
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 First seen · 120 lines · 26 tokens per session scan A a442ba333021
review-lead is an agent published in the GitHub repository rretsiem/opencode-hive (39 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 920 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
kimi-shim
Transports a single shell command invoking /.claude/scripts/kimi-shim.sh and returns stdout verbatim. Dispatches a one-shot prompt through the installed Kimi Code CLI. Do not use it for OpenCode provider routes.
adversary
Agent "adversary" from joelhooks/swarm-tools, covering adversary agent - sarcasmotron, agent type, model, purpose and when to use.
background-worker
Runs background-only tasks without MCP tool access.
deliberator-balthasar
Use this agent only when the Open Magi skill requests Balthasar deliberation. Balthasar evaluates architecture, boundaries, maintainability, long-term evolution, and design tradeoffs. Return a Magi report only; do not edit files or run commands.
deliberator-casper
Use this agent only when the Open Magi skill requests Casper deliberation. Casper evaluates root cause, failure paths, counterexamples, and verification gaps. Return a Magi report only; do not edit files or run commands.
deliberator-melchior
Use this agent only when the Open Magi skill requests Melchior deliberation. Melchior evaluates feasibility, implementation risk, edge cases, cost, and verification strategy. Return a Magi report only; do not edit files or run commands.