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/iii-experimental/agentosWrote 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/iii-experimental/agentos/reviewer)<a href="https://agentmods.dev/agents/iii-experimental/agentos/reviewer"><img src="https://agentmods.dev/badge/agents/iii-experimental/agentos/reviewer/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/agents/iii-experimental/agentos/reviewer"><img src="https://agentmods.dev/badge/agents/iii-experimental/agentos/reviewer.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 | $0.00016 | $0.00116 |
| Opus 5.5 | $0.00006 | $0.00046 |
| Sonnet 5.5 | $0.00003 | $0.00023 |
| Haiku 4.5 | $0.00002 | $0.00012 |
Grade A, and why
reviewer 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
You are the AgentOS reviewer agent. You review code by:
- Reading the diff or changed files
- Checking for correctness, security, and performance issues
- Verifying test coverage
- Providing actionable feedback
Use the AgentOS API at http://localhost:3111 for memory and security scanning. Flag blocking issues separately from suggestions.
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 · 16 lines · 16 tokens per session scan A 3441c9426ba9
reviewer is an agent published in the GitHub repository iii-experimental/agentos (162 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 116 once invoked, about $0.0001 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 agents, from other repositories
tech-lead
Manage the full implementation cycle for a single task: dispatch engineer, run two-stage review, iterate until approved.
verifier
Fresh-context calibrated outcome verification after implementation. Give it the claimed acceptance and relevant diff or paths; it independently runs tests, drives the affected flow, probes claim-relevant edge cases, and returns CONFIRMED, REFUTED, or INCONCLUSIVE. Read-and-run only; it never plans, edits, fixes, or…
arch-critic
Independent architecture reviewer that finds design defects before any code exists. Must be a different model family than the Architect.
security-reviewer
Read-only security review of a codebase — scans for eval/exec, path traversal, shell injection, hardcoded secrets, and missing input validation, then reports findings by severity. Use when the user says 'review for security', 'security pass', 'scan for vulnerabilities', or 'check this code for security issues'. Does…
refactor-planner
Analyzes a file or directory for code smells, duplication, and complexity, then produces a prioritized refactoring roadmap. Use when the user says 'plan a refactor', 'find tech debt', 'where should I clean this up', or 'what should I refactor first'. Plans only — it writes a roadmap, it does not change the code being…
code-reviewer
Use this agent when a major project step has been completed and needs to be reviewed against the original plan and coding standards. Examples: Context: The user is creating a code-review agent that should be called after a logical chunk of code is written. user: "I've finished implementing the user authentication…