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/CPUtester5465/countbean-pluginWrote 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/cputester5465/countbean-plugin/undo)<a href="https://agentmods.dev/commands/cputester5465/countbean-plugin/undo"><img src="https://agentmods.dev/badge/commands/cputester5465/countbean-plugin/undo/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/cputester5465/countbean-plugin/undo"><img src="https://agentmods.dev/badge/commands/cputester5465/countbean-plugin/undo.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 | $0.00015 | $0.00133 |
| Opus 5.5 | $0.00006 | $0.00053 |
| Sonnet 5.5 | $0.00003 | $0.00027 |
| Haiku 4.5 | $0.00002 | $0.00013 |
Grade A, and why
undo 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.
What it actually says
Help the user undo a change. Arguments: $ARGUMENTS (optional commit id).
- Call
historyto show recent commits. - If
$1is a commit id, callrevert(commit="$1"). Otherwise show the history and ask which change to undo. - Confirm the new state with
book_status.
Because every change is a git commit, reverting is always safe and itself recorded — nothing is lost, it's just a new commit that backs out the old one.
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 · 15 lines · 15 tokens per session scan A 70dfc85a011f
undo is a command published in the GitHub repository CPUtester5465/countbean-plugin (34 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 133 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 2026-08-30.
Other commands, from other repositories
audit
Scan for non-kernel money math. Rebuild critical flows as JournalEntrys. Replay and prove. Complements /ledger-verify.
reconcile
Assumptions → Money.from → cited, balanced JournalEntry → Ledger.apply. Output entries + proof.
turbo-spend
Report the turbo session's REAL cross-provider API spend against the operator-set ceiling (framework default $100, runtime-raisable), and assert the turbo permission-profile honesty invariant (push-to-main = confirm, never auto/notice). Report-only for spend; fail-open on a ledger fault. A NEW scan, separate from…
review
Kernel first (/ledger-verify or /ledger-audit), then host TDD/review/security if present. See skills/ledger-review/SKILL.md.
sim
Seeded scenario on the kernel. Log assumptions. Prove equation. Replay with the same seed must match.
correct
A command for correcting an incorrectly classified accounting transaction and saving the correction for future matching transactions.