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/jszmajda/lidWrote 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/jszmajda/lid/differential-audit)<a href="https://agentmods.dev/commands/jszmajda/lid/differential-audit"><img src="https://agentmods.dev/badge/commands/jszmajda/lid/differential-audit/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/jszmajda/lid/differential-audit"><img src="https://agentmods.dev/badge/commands/jszmajda/lid/differential-audit.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 | $0.00077 | $0.00210 |
| Opus 5.5 | $0.00031 | $0.00084 |
| Sonnet 5.5 | $0.00015 | $0.00042 |
| Haiku 4.5 | $0.00008 | $0.00021 |
Grade A, and why
differential-audit 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 1mo 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
Invoke the bidirectional-differential skill in command mode.
/differential-audit— opens the scoping conversation (interprets the user's description, maps to arrows, captures scope and runs-per-direction, confirms with a cost estimate)./differential-audit EXP-BIDIFF-001 KWP-UE-004— audits the listed EARS IDs directly using defaults fromCLAUDE.md's## LID Experimentalsection (default N=3).
See plugins/lid-experimental/skills/bidirectional-differential/SKILL.md for the full behavior.
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.
- 1mo ago First seen · 12 lines · 77 tokens per session scan A 06b1c5d41a96
differential-audit is a command published in the GitHub repository jszmajda/lid (112 stars, last pushed 6d ago), licensed MIT. It adds 77 tokens to every session and 210 once invoked, about $0.0003 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-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
release
Release manager for frontend and mobile. Writes App Store notes, user-facing changelog, flags stale docs and landing copy. Actions: notes | changelog | docs | sync.
review-skills
Review changed skills: automated bash checks + 9 structural dimensions (D1-D9) + 5 intent checks (M1-M5). PASS/FAIL verdict. Fix in-place.
revisar
Peer review estricto de código con análisis de rendimiento, arquitectura, seguridad y cumplimiento. Usa cuando el usuario dice "revisar código", "code review", "peer review", "revisame este archivo", "review my code", "analizar código", "revisar PR", "revisar feature". Incluye análisis de performance, security OWASP…
esp-teach
One-time project setup -- discover hardware, find datasheets, persist context to CLAUDE.md.
swift-critique
Critique SwiftUI code for patterns, design, clean code, accessibility, and performance.