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/khur/clawdbod/configgit clone --depth 1 https://github.com/khur/clawdbodWhat 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 | $0.00019 | $0.00582 |
| Opus 5 | $0.00010 | $0.00291 |
| Sonnet 5 | $0.00004 | $0.00116 |
| Haiku 4.5 | $0.00002 | $0.00058 |
Grade A, and why
config 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ClawdBod Config
First, read ~/.claude/clawdbod/config.json. If the file doesn't exist, silently create it (and the directory) with these defaults before continuing — do NOT mention the missing file to the user:
{
"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 (profile, etc.).
If $ARGUMENTS is empty — show current settings
ClawdBod Settings:
Break every N prompts: 8
Min minutes between: 20
Profile: set (6'4", 265 lbs, 40, male)
Data location: ~/.claude/clawdbod/ (local only)
If profile is set, show the details; otherwise show not set (add with /clawdbod:config profile). Then ask if they'd like to change anything.
If $ARGUMENTS contains "prompts" + a number
Update promptsBetweenBreaks in config.json. Confirm the change.
If $ARGUMENTS contains "minutes" + a number
Update minMinutesBetweenBreaks in config.json. Confirm the change.
If $ARGUMENTS contains "profile"
- Ask for all at once (all optional — they can skip any):
- Height (like 5'10 or 70 inches)
- Weight (lbs)
- Age
- Gender (male/female/other)
- Save to config.json as a
profileobject:
Convert feet/inches to total inches (5'10 = 70).{ "profile": { "height_inches": 70, "weight_lbs": 175, "age": 30, "gender": "male" } } - Confirm what was saved. Mention this enables calorie estimates and stays local.
If $ARGUMENTS contains "reset"
- Warn them: this resets break settings and profile to defaults. Their workout history (
workouts.jsonl) is NOT touched. - If they confirm, overwrite config.json with defaults only:
{ "promptsBetweenBreaks": 8, "minMinutesBetweenBreaks": 20 }
After any change, confirm what was updated and show the new settings. Keep it brief.
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 · 71 lines · 19 tokens per session scan A b3450d1df087
config is a command published in the GitHub repository khur/clawdbod (5 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 582 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 2026-08-31.
Other commands, from other repositories
README
Git workflow and quality assurance commands for the claude-skills repository.
validate
Validate a finding — runs 7-Question Gate + 4-gate checklist. Kills weak findings before report writing. Prevents N/A submissions that hurt validity ratio. Usage: /validate.
convert-to-todowrite-tasklist-prompt
Purpose: Transform verbose, context-heavy slash commands into efficient TodoWrite tasklist-based methods with parallel subagent execution for 60-70% speed improvements.
security-audit
Perform a comprehensive security audit of the codebase to identify potential vulnerabilities, insecure patterns, and security best practice violations.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
session-end
I'll summarize this coding session and update the memory system with our accomplishments.