Bernstein is an open-source governance layer for AI agents that applies written policies, schedules agent work deterministically, controls approvals, and records verifiable execution history. It is used to coordinate CLI coding agents and other agent workloads, including parallel runs and offline review, while the catalogue entries provide its agent workflows and controls.
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 skills add sipyourdrink-ltd/bernstein --skill reviewergit clone --depth 1 https://github.com/sipyourdrink-ltd/bernsteinWrote 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/skills/sipyourdrink-ltd/bernstein/reviewer)<a href="https://agentmods.dev/skills/sipyourdrink-ltd/bernstein/reviewer"><img src="https://agentmods.dev/badge/skills/sipyourdrink-ltd/bernstein/reviewer/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/skills/sipyourdrink-ltd/bernstein/reviewer"><img src="https://agentmods.dev/badge/skills/sipyourdrink-ltd/bernstein/reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00014 | $0.00322 |
| Opus 5 | $0.00007 | $0.00161 |
| Sonnet 5 | $0.00003 | $0.00064 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
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 9d 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
Code Reviewer Skill
You are a code reviewer. Review code for correctness, quality, maintainability, and adherence to standards.
Specialization
- Code correctness and logic verification
- Style consistency and coding standards enforcement
- Performance and security review
- Test coverage and test quality assessment
- API design and interface review
- Merge readiness evaluation
Work style
- Read the task description to understand what was changed and why.
- Read the diff or changed files thoroughly before commenting.
- Distinguish blocking issues from suggestions and nits.
- Provide specific, actionable feedback with examples or fixes.
- Approve when all blocking issues are resolved; do not block on style nits.
Rules
- Only modify files listed in your task's
owned_files(typically review notes). - Classify feedback: blocking / suggestion / nit.
- Check for: correctness, tests, types, error handling, security, performance.
- Verify the change does what the task description asks for.
- If a critical defect is found, post to BULLETIN immediately.
Call load_skill(name="reviewer", reference="review-rubric.md") for the
rubric, or reference="feedback-tone.md" for tone guidance.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 45 lines · 14 tokens per session scan A ab8dfcd9645e
reviewer is a skill published in the GitHub repository sipyourdrink-ltd/bernstein (1,126 stars, last pushed yesterday), licensed Apache-2.0. It adds 14 tokens to every session and 322 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 skills, from other repositories
process_prs
Use this skill to work the open PR queue end-to-end: assess merge readiness, run security gates, selectively request Claude Opus review on substantial PRs, merge eligible PRs, and hand off release PRs to /release.
review
Code review skill for PRs, branches, or uncommitted changes. Loads the appropriate subset of architecture/subsystem docs based on what changed, walks the changeguardrailsrules pre-PR checklist, and emits structured findings (blocking / advisory / nit) with a verdict.
create_pr
Open a high-quality pull request with a standardized description (Problems / Solutions / UX improvements / Documentation / Test plan / Breaking changes), the changeguardrailsrules.md pre-PR checklist enforced, and thorough functional-change documentation under docs/ surfaced via the docs server and docs site. Use this…
final-review
Skill "final-review" from markmhendrickson/neotoma, covering final review, trigger, tasks and inputs.
review-thread
Record review verdicts and run the StateNote review thread on an agent-operation instance — every ReviewRequest verdict is one atomic batch-direct-write that advances status and co-writes a reviewnote explaining why, and findings are corrected by appending notes rather than editing them.
reviewing-plan-docs
Review planning documents by reading the plan docs and doing a thorough codebase walkthrough, then writing detailed review docs. Use when the user asks to review, audit, critique, or validate a plan, design doc, or spec in the permit0 repository.