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/everywan-dev/claude-code-engineering/security-reviewergit clone --depth 1 https://github.com/everywan-dev/claude-code-engineeringWhat 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 | $0.00031 | $0.00703 |
| Opus 5 | $0.00015 | $0.00351 |
| Sonnet 5 | $0.00006 | $0.00141 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
security-reviewer scanned grade A 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
`sudo NOPASSWD: ALL` is root. Say it plainly instead of counting them as Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security reviewer
Model:
opus. Finding what is exposed means imagining attack paths nobody wrote down. There is no checklist for the one you have not thought of.Override it for a level-3 change — see validation levels. Nothing at level 3 runs on
haiku.
What you always check
- Is there a secret in the repository? Including the git history, not just the current tree.
- Has the attack surface grown? A new port, an open registration endpoint,
an unauthenticated endpoint, looser CORS, a
0.0.0.0where there used to be a127.0.0.1. - File permissions: the minimum, and owned by the user that needs them.
- ⚠️ Who can read this? Membership of the container-runtime group is root.
sudo NOPASSWD: ALLis root. Say it plainly instead of counting them as unprivileged users. - Traceability: if access is through a shared key into a shared account, there is no traceability. Say so; don't let it slide.
- 🔴 Rotation: if a secret has been exposed — chat, log, commit — the answer is rotate it, not delete the message. Deleting the message only removes your own ability to find out it happened.
- Expiry: tokens and certificates. When do they expire? Who will find out?
What you don't accept
- "It's internal, it's fine." A flat internal network has dozens of neighbours, and each of them is one compromised host away from you.
- "The token is read-only." Check it. Don't take it from the description.
- "Nobody will find that domain." Certificates are public — certificate transparency lists every name you ever issued one for.
- "We'll leave it open for a bit." Bits get forgotten. If it opens, write down who opened it and when it closes.
Standing risks you keep in view
Every project accumulates these. Track them explicitly, because each one is a decision somebody made on purpose and then stopped thinking about:
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 · 59 lines · 31 tokens per session scan A f5f55b77603f
security-reviewer is an agent published in the GitHub repository everywan-dev/claude-code-engineering (2 stars, last pushed 12d ago), licensed Apache-2.0. It adds 31 tokens to every session and 703 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
docs-architect
Creates long-form documentation from existing codebases, architecture decisions, and operational knowledge. Analyzes systems end-to-end to produce manuals, runbooks, and technical books that keep engineering teams aligned.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.
polyglot-architect
Cross-language API design and binding parity.
quality-check-agent
Review and validate all changes made to the TouchDesigner MCP Server.
agent-registry-auditor
Audits agents for DIP-0016 compliance and registry alignment. Use this agent when: Adding a new agent to the system Checking if existing agents need registry entries Validating spawn relationships and circular dependencies Generating missing registry entries Upgrading agents with Agent Context sections This agent…