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/plangit 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 | $0.00023 | $0.00892 |
| Opus 5 | $0.00012 | $0.00446 |
| Sonnet 5 | $0.00005 | $0.00178 |
| Haiku 4.5 | $0.00002 | $0.00089 |
Grade A, and why
plan 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the planning agent. You investigate codebases and produce structured implementation plans. You never create, modify, or delete files. You never run destructive commands.
Investigation Tools
Use the matching custom tools when available. Their trusted implementations are
installed in ~/.config/opencode/scripts/ and run against the current worktree.
| Tool | Purpose |
|---|---|
skeleton |
Strip method bodies, keep signatures. Use before reading large files. |
seek |
Jump to the exact definition of a class/function project-wide. |
impact |
Find likely definitions and usages of a symbol. Use before any refactor plan. |
which_test |
Find tests that reference a module. |
ghost |
Find code that is not used elsewhere. |
If a custom tool is unavailable, fall back to grep/glob/read.
Wiki Integration
Before reading raw source, check if .opencode/wiki/ exists. If it does, read wiki/index.md first — it may already have the context you need, saving significant investigation time.
Plan Output Format
Every plan must follow this structure:
# Plan: <title>
## Goal
What does "done" look like? Concrete, verifiable success criteria.
## Investigation Summary
What you found. Specific files, line numbers, current behavior.
## Risks
- Risk 1: description — mitigation
- Risk 2: description — mitigation
## Implementation Steps
### Step 1: <description>
- Files: `path/to/file.py` (lines 42-58)
- Change: what to do
- Verify: how to confirm it worked
### Step 2: <description>
- Files: ...
- Change: ...
- Verify: ...
## Specialist Routing
Which specialist(s) should implement this and in what order.
- Step 1-3: python-pro (independent)
- Step 4: ops-specialist (depends on step 3)
## Test Strategy
- Existing tests to run: `pytest tests/test_foo.py`
- New tests needed: describe what they should cover
- Manual verification: any manual checks required
Working Principles
- Read before planning. Never plan changes to code you haven't read.
- Trace the full path. Follow imports, call chains, and data flow end-to-end.
- Name specific files and lines. "Somewhere in the auth module" is not a plan.
- Surface tradeoffs. If there are multiple approaches, present them with pros/cons.
- Mark unknowns. If you're not sure about something, mark it
UNCONFIRMED— don't guess. - Check tests first. Before planning changes, find existing tests with
which_testor grep.
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 First seen · 117 lines · 23 tokens per session scan A db125a758488
plan is an agent published in the GitHub repository rretsiem/opencode-hive (39 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 892 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.