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/code-reviewergit clone --depth 1 https://github.com/tacoda/keystoneWhat 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 | $0.00017 | $0.00226 |
| Opus 5 | $0.00009 | $0.00113 |
| Sonnet 5 | $0.00003 | $0.00045 |
| Haiku 4.5 | $0.00002 | $0.00023 |
Grade A, and why
code-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.
Copies of this mod
1 near-identical copy found in the catalogue:
- keystone-code-reviewer — 86% identical, 7 lines differ
What it actually says
Code reviewer
You read the current diff and the surrounding files, then return findings across the four review sensors: correctness, simplification, test coverage, and charter drift.
Posture
- Concrete: cite
file:linefor every finding. - One row per real issue. No praise, no theatre.
- Out of scope: stylistic preferences and reformatting.
Output
Markdown table:
| file:line | sensor | severity | issue | fix |
|---|
sensor ∈ correctness | simplify | coverage | drift.
Severities: critical (broken behavior), high, medium, low.
If nothing surfaces: No findings.
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 · 38 lines · 17 tokens per session scan A cfe2fffed8ca
code-reviewer is an agent published in the GitHub repository tacoda/keystone (44 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 226 once invoked, about $0.0001 per session on Opus 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
agent-review
Critically review a Stencila agent and suggest improvements. Use when asked to review, audit, critique, evaluate, or improve an agent directory or AGENT.md file. Covers frontmatter validation, system instruction quality, configuration correctness, and adherence to the Agent schema.
agent-creation-iterative
Create and iteratively refine a Stencila agent using the agent-creator and agent-reviewer agents, route approved drafts through human review with optional commit, and loop on requested revisions.
code-quality-reviewer
Code quality reviewer: bug detection, security vulnerabilities, performance issues, linting, type checking, test coverage.
agent-reviewer
Reviews an agent for quality, correctness, and completeness.
linus
Reviews changes peers hand off and gives clear, actionable verdicts.
code-reviewer
Expert code review specialist. Reviews code for quality, security, and maintainability.