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/tacoda/keystone/keystone-review-securitygit clone --depth 1 https://github.com/tacoda/keystoneWrote 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/tacoda/keystone/keystone-review-security)<a href="https://agentmods.dev/agents/tacoda/keystone/keystone-review-security"><img src="https://agentmods.dev/badge/agents/tacoda/keystone/keystone-review-security.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.00235 |
| Opus 5 | $0.00016 | $0.00118 |
| Sonnet 5 | $0.00006 | $0.00047 |
| Haiku 4.5 | $0.00003 | $0.00023 |
Grade A, and why
keystone-review-security 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.
This is a copy
86% identical to review-security — 7 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.
What it actually says
Sensor: review-security
An agent reads the diff and reports security concerns — injection, auth, secrets, unsafe deserialization, weak crypto, missing authorization checks, dependency risk.
- Trigger — review (review phase).
- Inputs — the diff, the spec, and any relevant security-sensitive corpus (e.g.,
corpus/principles/secrets-management.md). - Exit condition — no blocking findings, or the user explicitly accepts the residual risk.
- Output — findings list keyed by file and line, each tagged blocking / nit / note, with the threat referenced.
- State writes — none.
How the agent is invoked is adapter-specific — sub-agent, separate session, MCP tool, or a checklist prompt — see .charter/adapters/<your-agent>/sensors.md. The bootstrap action records whether this sensor is available for the project's active adapter.
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.
- 2d ago First seen · 19 lines · 32 tokens per session scan A 515717451157
keystone-review-security is an agent published in the GitHub repository tacoda/keystone (44 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 235 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to review-security, differing in 7 lines, and is treated as a copy.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.