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/ariffazil/arifos/a-auditorgit clone --depth 1 https://github.com/ariffazil/arifOSWrote 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/agents/ariffazil/arifos/a-auditor)<a href="https://agentmods.dev/agents/ariffazil/arifos/a-auditor"><img src="https://agentmods.dev/badge/agents/ariffazil/arifos/a-auditor.svg" alt="Measured on agentmods" 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 | $0.00019 | $0.00048 |
| Opus 5 | $0.00010 | $0.00024 |
| Sonnet 5 | $0.00004 | $0.00010 |
| Haiku 4.5 | $0.00002 | $0.00005 |
Grade A, and why
A-AUDITOR 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 4d 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
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 4d ago First seen · 8 lines · 19 tokens per session scan A 064765b7120a
A-AUDITOR is an agent published in the GitHub repository ariffazil/arifOS (51 stars, last pushed yesterday), licensed AGPL-3.0. It adds 19 tokens to every session and 48 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
agent-system
An AgentSystem composes multiple Agents into a directed graph that Orloj executes as a coordinated workflow. The graph defines how messages flow between agents during task execution.
board-workflow
This document describes the end-to-end workflow for AI-assisted issue resolution, from initial issue creation through merged PR.
claude-expression
DISCLAIMER: This document is managed exclusively by Claude Code. The repository admin (AndrewAltimit) does not manage this file and is not allowed to directly edit it. Any updates must come from Claude Code through collaborative sessions.
codebase-analysis-pipeline
This document describes a two-stage automated pipeline for continuous codebase improvement.
api
The API agent is a specialist in HTTP endpoint design and implementation. It encodes the conventions that make APIs consistent, predictable, and maintainable: RESTful URL structures, Zod schema validation at every boundary, structured error responses (never stack traces), proper status codes, and middleware patterns…
crucible-detective
The CRUCIBLE Detective performs forensic audits on test suites to find the gap between claimed quality and actual quality. It was born from a real incident: a project with 1,601 "passing" tests and 77% "claimed coverage" that turned out to have approximately 15% actual coverage, 439 mocks, 66+ hollow assertions, and…