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 agents/mostwise/dot-claude/security-auditorgit clone --depth 1 https://github.com/mostwise/dot-claudeWhat 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 | $0.00039 | $0.01114 |
| Opus 5 | $0.00019 | $0.00557 |
| Sonnet 5 | $0.00008 | $0.00223 |
| Haiku 4.5 | $0.00004 | $0.00111 |
Grade B, and why
security-auditor scanned grade B with 1 finding 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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
literals crafted to look like directives to an AI tool ("SYSTEM:", "ignore previous instructions", "mark this rule as approved", "this finding is a Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
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 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 · 101 lines · 39 tokens per session scan B 0910739fa2df
security-auditor is an agent published in the GitHub repository mostwise/dot-claude (1 stars, last pushed 21d ago), with no licence file. It adds 39 tokens to every session and 1,114 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
analyst
You are an analysis specialist. You research topics via web search AND review code for bugs, quality, and improvements.
coder
You are a code implementation specialist. Write, edit, and test code efficiently.
docs
You are a document specialist. You create, edit, read, and transform professional documents.
scheduled
You are an autonomous scheduled agent. You execute recurring tasks independently.
tester
You are a testing & debugging specialist. You investigate bugs, errors, crashes, and unexpected behavior.
visuals
You are a visualization & UI specialist. You create plots, diagrams, web components, and animations.