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/mathaix/openclawmachines/prgit clone --depth 1 https://github.com/mathaix/OpenClawMachinesWhat 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 | $0.00000 | $0.00441 |
| Opus 5 | $0.00000 | $0.00220 |
| Sonnet 5 | $0.00000 | $0.00088 |
| Haiku 4.5 | $0.00000 | $0.00044 |
Grade A, and why
pr 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.
What it actually says
Commit all changes, push to remote, and create a pull request.
Instructions
-
First, gather information in parallel:
- Run
git statusto see untracked and modified files - Run
git diffto see staged and unstaged changes - Run
git log -5 --onelineto see recent commit message style - Run
git branch --show-currentto get current branch name - Check if branch tracks remote:
git rev-parse --abbrev-ref @{upstream} 2>/dev/null
- Run
-
Analyze all changes and draft a commit message:
- Summarize the nature of changes (feature, fix, refactor, etc.)
- Write a concise commit message focusing on "why" not "what"
- Do NOT commit binaries, .db files, or secrets (.env, credentials)
-
Stage and commit:
- Add relevant files with
git add - Create commit with message ending with the Claude Code signature:
🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <[email protected]> - Add relevant files with
-
Push to remote:
- Push with
git push origin <branch-name> - If branch doesn't exist on remote, use
git push -u origin <branch-name>
- Push with
-
Create the PR:
- Use
gh pr createwith a descriptive title and body - Include a Summary section with 1-3 bullet points
- Include a Test plan section with checkboxes
- End with the Claude Code signature
- Use
-
Return the PR URL to the user.
Example PR format
gh pr create --title "feat: description of change" --body "$(cat <<'EOF'
## Summary
- First key change
- Second key change
## Test plan
- [ ] Test item 1
- [ ] Test item 2
🤖 Generated with [Claude Code](https://claude.com/claude-code)
EOF
)"
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 · 54 lines · 0 tokens per session scan A fe4f9cdb985e
pr is a command published in the GitHub repository mathaix/OpenClawMachines (57 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 441 tokens. 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 commands, from other repositories
status
Show current Bernstein orchestration status.
tokenless-stats
Show Tokenless compression statistics.
triage-pr
Triage a PR — classify, optionally fix, optionally enable auto-merge.
buzz-crawling
外部舆情策略更新全流程 — /buzz-crawling run 启动外部舆情策略更新全流程.
cct-sop-alert
营销智评分流(告警测试) — 测试钉钉告警通知的分流工作流,botId带test前缀会触发失败.
riskreview
The user invoked the /riskreview facade command from the risk-review-pipeline pack.