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.
git 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/glm)<a href="https://agentmods.dev/commands/kckylechen1/clankerhouse/glm"><img src="https://agentmods.dev/badge/commands/kckylechen1/clankerhouse/glm/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/commands/kckylechen1/clankerhouse/glm"><img src="https://agentmods.dev/badge/commands/kckylechen1/clankerhouse/glm.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 | $0.00014 | $0.00507 |
| Opus 5.5 | $0.00006 | $0.00203 |
| Sonnet 5.5 | $0.00003 | $0.00101 |
| Haiku 4.5 | $0.00001 | $0.00051 |
Grade A, and why
glm 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 2mo 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
83% identical to deepseek — 12 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 Clanker: GLM by invoking the clanker:oc subagent via the Agent tool (subagent_type: "clanker:oc"). The fixed model token is glm.
Raw request: $ARGUMENTS
Argument mapping:
- Fixed
model: "glm"; do not ask the user for a model and do not infer another one. --writepresent ->read_only: falseand aworktreeis mandatory. If the user did not name a branch, generateclanker/glm-<short-timestamp>. Absent--write->read_only: true.--effort <effort>->effort; the backend may return a warning if Opencode ignores it.- Everything else is the natural-language
prompt. --backgroundand--waitare Claude execution flags. Do not forward them to the Clanker prompt.
Execution mode:
- If the raw request includes
--wait, runclanker:ocin the foreground and relay its final result verbatim. - If the raw request includes
--background, runclanker:ocas a Claude Code background task withrun_in_background: true. - If neither flag is present, default to background.
Background flow:
- Launch exactly one
Agenttool call withsubagent_type: "clanker:oc"andrun_in_background: true. - The task text must be: "Dispatch as Clanker: GLM. prompt=. read_only=. worktree=. model=glm. 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: GLM 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.
- 2mo ago First seen · 39 lines · 0 tokens per session scan A 3cf49de285d6
glm is a command published in the GitHub repository kckylechen1/ClankerHouse (0 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 507 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 83% identical to deepseek, differing in 12 lines, and is treated as a copy.
glm compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| glmkckylechen1/ClankerHouse | Command | 0 | 4mo ago | MIT | A | 14 | Claude Code |
| checklistgithub/spec-kit | Command | 150k | 3d ago | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 150k | 3d ago | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 150k | 3d ago | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 150k | 3d ago | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 150k | 3d ago | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 150k | 3d ago | MIT | A | 14 | Claude Code |