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 daanvandenbergh/claudekit --skill audit-deep-logicgit clone --depth 1 https://github.com/daanvandenbergh/claudekitWrote 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/daanvandenbergh/claudekit/audit-deep-logic)<a href="https://agentmods.dev/skills/daanvandenbergh/claudekit/audit-deep-logic"><img src="https://agentmods.dev/badge/skills/daanvandenbergh/claudekit/audit-deep-logic/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/daanvandenbergh/claudekit/audit-deep-logic"><img src="https://agentmods.dev/badge/skills/daanvandenbergh/claudekit/audit-deep-logic.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 | $0.00000 | $0.07704 |
| Opus 5.5 | $0.00000 | $0.03082 |
| Sonnet 5.5 | $0.00000 | $0.01541 |
| Haiku 4.5 | $0.00000 | $0.00770 |
Grade A, and why
audit-deep-logic 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
3 files 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.
- 2mo ago First seen · 447 lines · 0 tokens per session scan A d888b53e9f7c
audit-deep-logic is a skill published in the GitHub repository daanvandenbergh/claudekit (2 stars, last pushed 27d ago), with no licence file. It costs nothing until one of its globs matches a file; then it loads 7,704 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 2026-08-31.
audit-deep-logic compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| audit-deep-logicdaanvandenbergh/claudekit | Skill | 2 | 27d ago | none | A | 0 | Claude Code |
| time-bomb-radarTerryc21/radar-suite | Skill | 20 | 18d ago | Apache-2.0 | A | 80 | Claude Code |
| radar-suite-axis-classificationTerryc21/radar-suite | Skill | 20 | 18d ago | Apache-2.0 | A | 77 | Claude Code |
| senior-engineering-partnerbjgreenberg/senior-engineering-partner | Skill | 190 | yesterday | Apache-2.0 | C | 244 | Claude Code |
| code-quality-loopNYTC69/review-loop | Skill | 3 | 2d ago | Apache-2.0 | A | 76 | Claude Code |
| concept-auditontology-of-everything/SemanticSkills | Skill | 8 | 1mo ago | Apache-2.0 | A | 41 | Codex |
| dotnet-techne-refactor-pipelineMetalnib/dotnet-episteme-skills | Skill | 12 | 1mo ago | MIT | A | 113 | Claude Code |