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/sandeep-alluru/clickproof/pr-prepgit clone --depth 1 https://github.com/sandeep-alluru/clickproofWhat 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 | $0.00184 |
| Opus 5 | $0.00000 | $0.00092 |
| Sonnet 5 | $0.00000 | $0.00037 |
| Haiku 4.5 | $0.00000 | $0.00018 |
Grade A, and why
pr-prep 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 yesterday.
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
100% identical to pr-prep — 0 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
Run the full pre-PR checklist and report what's ready and what needs fixing.
Steps:
- Run lint:
make lint(ruff check + ruff format --check) - Run type check:
make typecheck(mypy) - Run tests:
make test(pytest with coverage) - Check CHANGELOG.md has an entry under [Unreleased] for this change
- Check that no debug print() statements or TODO comments were left in modified files
Report in this format: ✅ Lint — clean ✅ Types — clean ✅ Tests — 43 passed, 87% coverage ⚠️ CHANGELOG — no [Unreleased] entry found ✅ No debug artifacts
If anything fails, show the exact error and the file:line to fix. Do not mark the PR ready until all 5 checks pass.
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.
- yesterday First seen · 19 lines · 0 tokens per session scan A bdaef57ccde0
pr-prep is a command published in the GitHub repository sandeep-alluru/clickproof (0 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 184 tokens. A static security scan graded it A with 0 findings. It is 100% identical to pr-prep, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
axstream-teach
Compile a UI task into a fast replayable macro (do it once, instant forever).
axstream
Status of fast computer use — macro library, verified state, prerequisites.
axstream-stats
Benchmark a macro and show the speed story (p50/p95 per op).
CHANGELOG
Command "CHANGELOG" from bytedance/UI-TARS-desktop, covering 0.4.0 2024-12-10 - add logging, 1.2.29, 1.2.28, 1.2.26 and 1.2.25.
run
显式启动一次隔离的 Windows Computer Use 任务.
doctor
检查 Computer Use 插件、环境和 Reasonix 能力映射.