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/khur/clawdbodWrote 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/khur/clawdbod/setup)<a href="https://agentmods.dev/commands/khur/clawdbod/setup"><img src="https://agentmods.dev/badge/commands/khur/clawdbod/setup/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/khur/clawdbod/setup"><img src="https://agentmods.dev/badge/commands/khur/clawdbod/setup.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 | $0.00020 | $0.00664 |
| Opus 5.5 | $0.00008 | $0.00266 |
| Sonnet 5.5 | $0.00004 | $0.00133 |
| Haiku 4.5 | $0.00002 | $0.00066 |
Grade A, and why
setup 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 1mo 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ClawdBod Setup
Walk the user through onboarding. First, read ~/.claude/clawdbod/config.json. If it doesn't exist, silently create it (and the directory) with these defaults before continuing:
{
"promptsBetweenBreaks": 8,
"minMinutesBetweenBreaks": 20
}
IMPORTANT: When writing config.json, always read the existing file first and merge your changes into it. Never overwrite the whole file — preserve all existing fields.
Flow
Step 1 — Welcome
If they already have a profile in config.json — they're fully set up:
You're already set up! Everything looks good:
Profile: set (6'4", 265 lbs, 40, male)
Breaks: every 8 prompts (20 min cooldown)
Need to change anything? Try /clawdbod:config
If they're brand new (no profile):
Let's get you set up on ClawdBod — takes about 30 seconds.
Breaks are currently every 8 prompts with a 20 minute cooldown. Want to change that, or keep the defaults?
Apply any cadence changes to config.json, then move to Step 2.
Step 2 — Profile (optional but encouraged)
Quick optional step — sharing a couple details lets me estimate calories burned during breaks. This stays in a local file on your machine and is never uploaded anywhere.
- Height? (like 5'10 or 70 inches)
- Weight in lbs?
- Age?
- Gender? (male/female/other)
Or just say "skip" to skip all of this.
If they provide values:
- Convert feet/inches to total inches (5'10 = 70, 6'1 = 73, etc.)
- Read existing config.json, merge in the
profileobject, write it back:{ "profile": { "height_inches": 70, "weight_lbs": 175, "age": 30, "gender": "male" } }
If they say "skip" — that's fine, move to Step 3.
Step 3 — Confirm
You're all set!
Profile: set (5'10", 175 lbs, 30, male)
Breaks: every 8 prompts (20 min cooldown)
Your data: ~/.claude/clawdbod/ (local only)
Every break gets logged automatically. Check your stats with /clawdbod:history, or export everything with /clawdbod:export.
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.
- 1mo ago First seen · 82 lines · 20 tokens per session scan A 71e6dccb7463
setup is a command published in the GitHub repository khur/clawdbod (5 stars, last pushed 2d ago), licensed MIT. It adds 20 tokens to every session and 664 once invoked, about $0.0001 per session on Opus 5.5. 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 commands, from other repositories
evaluate
You are running the evaluation phase of the current Grainulator sprint. This is the honesty phase — where claims meet data.
prototype
You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.
next
Read the active sprint’s current status. Refresh stale compilation using grainulator compile --dir or grainulator.compile. Use the resulting nextactions with the user’s current scope and authorization. Output only the two Auto and Manual lists below, with no recap, status counters or offer to continue. Continue useful…
post
Post the current OCR review to a GitHub PR.
show
Display a past OCR review session.
history
List past OCR review sessions.