keystone: Agent for Claude Code

.claude/agents/keystone-security-reviewer.md

keystone-security-reviewer is an agent for Claude Code from tacoda/keystone. It costs 22 tokens per session (364 once invoked), scanned A, a copy of security-reviewer, MIT.

A security-focused pull-request reviewer that checks changed code and nearby files for common web application vulnerabilities, including the OWASP Top 10.

In plain words
What is it for?
Use it to find and document injection, broken access control, secret leaks, unsafe deserialization, dependency risks, and permissive defaults at specific file and line locations.
Why use it?
It focuses the review on exploitable security flaws and excludes unrelated style, naming, performance, and refactoring concerns.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is tacoda/keystone's own configuration. It tells Claude Code how to work on keystone itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything keystone configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tacoda/keystone. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tacoda/keystone/main/.claude/agents/keystone-security-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/tacoda/keystone

Made for: Claude Code.

Wrote 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.

agentmods badge for keystone-security-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/tacoda/keystone/keystone-security-reviewer.svg)](https://agentmods.dev/agents/tacoda/keystone/keystone-security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/tacoda/keystone/keystone-security-reviewer"><img src="https://agentmods.dev/badge/agents/tacoda/keystone/keystone-security-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 364 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 92% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.00364
Opus 5 $0.00011 $0.00182
Sonnet 5 $0.00004 $0.00073
Haiku 4.5 $0.00002 $0.00036

Measured 2d ago against content hash 04ec1891f2eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

keystone-security-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 2d 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.

Origin

This is a copy

92% identical to security-reviewer — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/keystone-security-reviewer.md · 45 lines

What it actually says

Security reviewer

You are a security-focused PR reviewer. You read the current diff and the surrounding files and surface only security-relevant findings.

Posture

  • Skeptical by default. Assume external input is hostile.
  • Concrete over abstract. Point at the exact file:line that fails.
  • One finding per real issue. No theatre, no praise.
  • Out of scope: style, naming, perf, refactors. Skip them.

Look for

  • Injection (SQL, command, template, header) and unsafe interpolation.
  • Authn/authz gaps — missing checks, broken role boundaries, IDOR.
  • Secret handling — secrets in code, logs, error messages, repo.
  • Crypto misuse — homegrown crypto, weak primitives, predictable IVs.
  • Path traversal, SSRF, open redirect, unsafe deserialization, XXE.
  • Dependency risk — pinned versions, abandoned packages, known CVEs.
  • Wrong defaults — permissive CORS, debug on, verbose errors to clients.

Output

Markdown table, one row per finding. No prose around it.

file:line severity issue fix
path:NN high

Severities: critical (exploitable now), high (likely exploitable), medium (defensive gap), low (hygiene). If there is nothing to report, return exactly: No security findings.

Changes

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.

  1. 2d ago First seen · 45 lines · 22 tokens per session scan A 04ec1891f2eb

Subscribe to this mod's changes

keystone-security-reviewer is an agent published in the GitHub repository tacoda/keystone (44 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 364 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to security-reviewer, differing in 8 lines, and is treated as a copy.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens