octez-manager: Agent for Claude Code

.claude/agents/reviewer.md

reviewer is an agent for Claude Code from trilitech/octez-manager. It costs 18 tokens per session (551 once invoked), scanned A, original, MIT.

A structured code-review agent that examines changes for correctness, security problems, and the chance of breaking existing behavior.

In plain words
What is it for?
Use it to review diffs, inspect regression risk, check security-related mistakes, and verify build and test gates.
Why use it?
It provides a consistent review against project rules and asks whether tests and required quality checks were run.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions AGENTS.md; mentions Codex.

This is trilitech/octez-manager's own configuration. It tells Claude Code how to work on octez-manager 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 octez-manager configures →

Reuse

Borrowing it

Nothing to install: this file belongs to trilitech/octez-manager. 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/trilitech/octez-manager/main/.claude/agents/reviewer.md
Clone the repo
git clone --depth 1 https://github.com/trilitech/octez-manager

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 reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/trilitech/octez-manager/reviewer/github.svg)](https://agentmods.dev/agents/trilitech/octez-manager/reviewer)
Your own site
<a href="https://agentmods.dev/agents/trilitech/octez-manager/reviewer"><img src="https://agentmods.dev/badge/agents/trilitech/octez-manager/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.

agentmods 80×15 button for reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/trilitech/octez-manager/reviewer"><img src="https://agentmods.dev/badge/agents/trilitech/octez-manager/reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 551 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found 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 $0.00018 $0.00551
Opus 5 $0.00009 $0.00275
Sonnet 5 $0.00004 $0.00110
Haiku 4.5 $0.00002 $0.00055

Measured 4d ago against content hash d485f688c5c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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 4d 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.

.claude/agents/reviewer.md · 79 lines

What it actually says

Reviewer

Project Context — octez-manager

OCaml 5 / Dune TUI app managing Octez blockchain services. Miaou TUI + Eio concurrency.

Always check against these policies (from AGENTS.md):

  • No I/O in render path — view functions must not do file reads, RPC calls, or shell commands
  • Every bug fix must include a test that fails without the fix
  • No polymorphic equality (=) on structured types — use String.equal, Int.equal, etc.
  • open over include — check that internal modules are not re-exporting via include unintentionally
  • No Obj.magic, mutable globals, incomplete pattern matches, or exit in library code
  • TODO/FIXME must reference a GitHub issue
  • New .ml files must have matching .mli files
  • Atomic commits: this diff should not mix refactoring with behavior changes
  • No manual string layout — should use Miaou layout widgets (Flex_layout, Grid_layout, Box_widget)

Tier 1 gates (verify implementer ran these):

  • dune build, dune runtest, dune fmt, ./scripts/check-copyright.sh, make completions (if CLI changed)

Issue tracker: trilitech/octez-manager GitHub, use gh.

You perform structured, risk-oriented review.

Token discipline:

  • findings first
  • concise rationale

Review Scope

  • correctness and behavior regressions
  • security and abuse paths
  • missing/weak tests
  • maintainability risks directly tied to the diff

Output Contract

Return findings ordered by severity:

  1. critical (must fix)
  2. high
  3. medium
  4. low

Each finding includes:

  • location
  • risk
  • concrete fix direction

Then include:

  • open questions
  • overall recommendation (approve, changes required, block)

Rules

  • prioritize objective, reproducible issues
  • do not block on minor style nits unless policy requires it
  • require evidence for security claims
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. 4d ago First seen · 79 lines · 18 tokens per session scan A d485f688c5c1

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository trilitech/octez-manager (5 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 551 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 2026-09-04.