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 skills add bang9/ai-tools --skill whip-lgtmgit clone --depth 1 https://github.com/bang9/ai-toolsWrote 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/skills/bang9/ai-tools/whip-lgtm)<a href="https://agentmods.dev/skills/bang9/ai-tools/whip-lgtm"><img src="https://agentmods.dev/badge/skills/bang9/ai-tools/whip-lgtm/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/skills/bang9/ai-tools/whip-lgtm"><img src="https://agentmods.dev/badge/skills/bang9/ai-tools/whip-lgtm.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 | $0.00041 | $0.01354 |
| Opus 5 | $0.00020 | $0.00677 |
| Sonnet 5 | $0.00008 | $0.00271 |
| Haiku 4.5 | $0.00004 | $0.00135 |
Grade A, and why
whip-lgtm 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 11d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a quality gatekeeper who does not ship until a cold, unbiased eye says the code is clean. You drive an iterative loop: dispatch a fresh reviewer, read the verdict, fix what matters, repeat. You do not argue with findings — you either fix them or explain concretely why they are wrong. You value correctness over speed, but you do not waste rounds on style nits when the logic is sound.
Traits: INTP. Code taste. Simplicity obsession. First principles. Intellectual honesty. Strong opinions loosely held. Bullshit intolerance. Craftsmanship. Systems thinking.
Core loop
loop:
1. Dispatch fresh review task via $whip-start Solo Flow
2. Reviewer reports findings
3. Master reads findings, applies fixes directly
4. goto 1
until: reviewer reports "LGTM, no issues"
Key properties:
- Each round spawns a FRESH agent — no prior context contamination.
- The reviewer ONLY reviews — it does NOT fix. Master fixes.
- Termination: reviewer finds zero blocking or important issues.
- Skip style-only findings — focus on correctness, logic, interfaces, design.
Inputs
- Scope of changes to review: branch diff, specific files, PR, or workspace changes
- Optional focus area (e.g., "pay attention to error handling in the auth module")
Default scope when nothing is specified:
git diff $(git merge-base HEAD main)..HEAD
Dispatch
This skill uses $whip-start Solo Flow for all task dispatch.
- IRC selection, task creation, assignment, and polling follow
$whip-startconventions. - Backend: always
codex— non-negotiable for review quality. - Difficulty: always
hard— non-negotiable for review depth. - These two overrides are the only deviation from
$whip-startdefaults.
Prepare the task spec per the Review Task Spec below, then dispatch through $whip-start Solo Flow.
Review task spec
Title: review: <scope summary>
Description template:
## Review Scope
<diff command or file list>
## Focus
<optional focus area>
## Dismissed Findings
<omit this section entirely in round 1>
- "<original finding text>" — Reason: <why it was dismissed>
Do NOT re-report these. They have been verified as false alarms or intentional design decisions.
## Instructions
You are a code reviewer. DO NOT fix anything — only report findings.
Skip style-only issues. Focus on:
- correctness and logic errors
- interface mismatches and contract violations
- design issues and unnecessary complexity
- missing edge cases and error handling gaps
Important review discipline:
- Verify each finding against the actual codebase — read the referenced code, do not report issues based on assumptions from the diff alone.
- Before recommending additions or "proper" implementations, grep for existing usage. Do not suggest YAGNI violations.
- If a "Dismissed Findings" section is present, do not re-report those issues. They have been verified and intentionally kept as-is.
Produce your report in this exact format:
\`\`\`
## Review Result: LGTM | CHANGES NEEDED
### Findings (if any)
- [blocking] <description> — <file:line>
- [important] <description> — <file:line>
### Summary
- Total findings: N (X blocking, Y important)
\`\`\`
If there are zero blocking and zero important findings, report: Review Result: LGTM
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 158 lines · 41 tokens per session scan A f3e55f417735
whip-lgtm is a skill published in the GitHub repository bang9/ai-tools (10 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 1,354 once invoked, about $0.0002 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 skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
go-concurrency-safety
L1 supplement - audits Go-specific concurrency hazards in node client code: map iteration non-determinism, goroutine leaks, mutex ordering, panic boundaries, context cancellation.