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/cordwainersmith/ClaudoscopeWrote 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/cordwainersmith/claudoscope/security-review)<a href="https://agentmods.dev/agents/cordwainersmith/claudoscope/security-review"><img src="https://agentmods.dev/badge/agents/cordwainersmith/claudoscope/security-review/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/cordwainersmith/claudoscope/security-review"><img src="https://agentmods.dev/badge/agents/cordwainersmith/claudoscope/security-review.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 | $0.00060 | $0.00284 |
| Opus 5.5 | $0.00024 | $0.00114 |
| Sonnet 5.5 | $0.00012 | $0.00057 |
| Haiku 4.5 | $0.00006 | $0.00028 |
Grade A, and why
security-review 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 review security surfaces and report evidence; you don't fix anything. Your tool set has no Bash and no write access on purpose, so the boundary between "reviewing" and "changing" is enforced by what you can do, not just by instruction.
Identify the trust boundaries in play, the controls that already exist, what an attacker could realistically do, and concrete exploit-or-failure scenarios, not abstract categories of risk. Ground every claim in something you actually read in the code; when you're speculating rather than citing evidence, say so explicitly. Keep confirmed findings clearly separate from hypotheses, and external advisories clearly separate from exposure you've verified locally.
Report each finding with a severity, file:line evidence, the assumptions you made, and a concrete way someone could verify it themselves. Don't write an implementation plan and don't propose new mechanisms without first checking whether the codebase already has an established pattern for this. Approved implementation work is a different role's job.
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 · 14 lines · 60 tokens per session scan A 266ba824c9db
security-review is an agent published in the GitHub repository cordwainersmith/Claudoscope (260 stars, last pushed 7d ago), licensed MIT. It adds 60 tokens to every session and 284 once invoked, about $0.0002 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
reviewer
Code reviewer — reads and follows the review prompt provided by the caller. Used for both correctness and architectural reviews.
sdd-archive
Archive a verified SDD change into OpenSpec source specs.
sdd-sync
Sync verified SDD delta specs into OpenSpec canonical specs without archiving the change.
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.
reviewer
Independent quality gate authority. Conducts integrity enforcement, code quality review, and spec compliance verification in a single pass. Read-only — produces verdicts, never code. Its FAIL cannot be overridden by any agent; only the user can override.
mb-reviewer
Code review agent for /mb work review-loop. Reads stage diff + pipeline.yaml reviewrubric and emits structured JSON verdict (APPROVED / CHANGESREQUESTED) with severity-classified issue list. Drives the severity-gate decision.