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 commands/kckylechen1/clankerhouse/ocgit clone --depth 1 https://github.com/kckylechen1/ClankerHouseWrote 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/commands/kckylechen1/clankerhouse/oc)<a href="https://agentmods.dev/commands/kckylechen1/clankerhouse/oc"><img src="https://agentmods.dev/badge/commands/kckylechen1/clankerhouse/oc.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.00850 |
| Opus 5 | $0.00010 | $0.00425 |
| Sonnet 5 | $0.00004 | $0.00170 |
| Haiku 4.5 | $0.00002 | $0.00085 |
Grade A, and why
oc 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 4d 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.
This is a copy
81% identical to codex — 26 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Dispatch the task below to the Clanker: Opencode by invoking the clanker:oc subagent via the Agent tool (subagent_type: "clanker:oc"). The subagent is a zero-discretion relay: it calls clanker_dispatch_start once and long-polls clanker_wait until the turn completes, its transcript showing the progress digests. Its final message (final_message + result fields) is what you relay to the user.
Raw request: $ARGUMENTS
Argument mapping (resolve these, then pass explicit parameters to the subagent):
- Model token (first token if it is a shortname, or a
--modelvalue): pass it through asmodelunchanged — the server resolves shortnames from the single source insrc/constants.ts(OC_MODEL_ALIASES). For reference, the current map isglm → zhipuai-coding-plan/glm-5.2,ds → deepseek/deepseek-v4-pro,kimi → kimi-for-coding/k2p6,free → opencode/deepseek-v4-flash-free; a value containing/is a full id. If no model token is given, default toglm. --writepresent →read_only: falseand aworktreeis mandatory (the server rejects a write without one). If the user did not name a branch, generate a defaultworktreelikeclanker/oc-<short-timestamp>. Absent--write(or--read-onlypresent) →read_only: true(safe default; the Clanker cannot modify files, no worktree needed).--effort <effort>→effort. Note: the opencode ACP lane does not support a reasoning-effort override; the lane returns a warning and ignores it (surfaced verbatim).- Everything that is not a recognized flag or the model token is the natural-language
prompt. Do not forward the flags themselves as prompt text. --backgroundand--waitare Claude execution flags. Do not forward them to the Clanker prompt, and do not treat them as part of the natural-language task text.
Execution mode:
- If the raw request includes
--wait, run theclanker:ocsubagent in the foreground and relay its final result verbatim. - If the raw request includes
--background, run theclanker:ocsubagent as a Claude Code background task withrun_in_background: true. - If neither flag is present, default to background. The whole point of this command is that Claude Code owns the visible Clanker task row; the MCP server only owns the ACP backend.
Background flow:
- Launch exactly one
Agenttool call withsubagent_type: "clanker:oc"andrun_in_background: true. - The task text must be: "Dispatch as this Clanker. prompt=. read_only=. worktree=. model=<token, e.g. glm or zhipuai-coding-plan/glm-5.2>. effort=. Follow your relay protocol."
- Do not call MCP dispatch tools in the main conversation.
- Do not wait for the subagent or relay a final result in this turn.
- After launching, tell the user: "Clanker: Opencode started in the Claude Code background task list."
Foreground flow:
- Launch exactly one
Agenttool call withsubagent_type: "clanker:oc"and no background flag. - Use the same task text as the background flow.
- Relay the subagent's final result verbatim.
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.
- 4d ago First seen · 39 lines · 0 tokens per session scan A 4cbad32adc9d
oc is a command published in the GitHub repository kckylechen1/ClankerHouse (0 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 850 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 81% identical to codex, differing in 26 lines, and is treated as a copy.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.