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/sam-agents/samWrote 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/sam-agents/sam/cosmo)<a href="https://agentmods.dev/agents/sam-agents/sam/cosmo"><img src="https://agentmods.dev/badge/agents/sam-agents/sam/cosmo/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/sam-agents/sam/cosmo"><img src="https://agentmods.dev/badge/agents/sam-agents/sam/cosmo.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 | $0.00011 | $0.00030 |
| Opus 5.5 | $0.00004 | $0.00012 |
| Sonnet 5.5 | $0.00002 | $0.00006 |
| Haiku 4.5 | $0.00001 | $0.00003 |
Grade A, and why
cosmo 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
$include: ../../../../../_sam/agents/css-reviewer.md
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 · 6 lines · 11 tokens per session scan A c419f50124a9
cosmo is an agent published in the GitHub repository sam-agents/sam (19 stars, last pushed 3mo ago), licensed MIT. It adds 11 tokens to every session and 30 once invoked, about $0.0000 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
parity-auditor
Audit code migrations for missing functionality. Compares source (legacy) against target (new) to find gaps in behavior, edge cases, i18n, and tests.
reviewer
Degraded-path fallback for /review's correctness + security dimensions (per SPEC-019), plus the kit-distinctive over-engineering minimality axis which runs on BOTH paths. On the primary path, kit /review delegates correctness + security to runtime /code-review and /security-review; this agent then runs only the…
ui-reviewer
Audit the design IMPLEMENTATION (rendered state coverage, copy usage, token usage in code, interaction fidelity, accessibility in code, component existence) — implementation-level only. System-level checks belong to design-auditor.
perf-auditor
Read-only frontend performance audit — bundle size and Core Web Vitals risks. Invoke from review, or for a performance pass on a web app.
gamedev-lead-programmer
You are the Lead Programmer for an indie game project. You translate the technical director's architectural vision into concrete code structure, review all programming work, and ensure the codebase remains clean, consistent, and maintainable.
docs-reviewer
Use when you need a read-only quality review of documentation — verifying technical accuracy against the code, audience fit, terminology and style consistency, link health, and whether every example actually runs.