octez-manager: Agent for Claude Code

.claude/agents/expert-debugger.md

expert-debugger is an agent for Claude Code from trilitech/octez-manager. It costs 20 tokens per session (590 once invoked), scanned A, original, MIT.

A debugging agent for investigating unclear build, dependency, integration, concurrency, and runtime failures. It reproduces terminal-interface problems and examines likely causes in the code and build setup.

In plain words
What is it for?
Use it to diagnose OCaml and Dune build failures, concurrency issues, integration-test problems, and terminal rendering bugs.
Why use it?
It gives a structured way to distinguish stale build files, missing libraries, type errors, deadlocks, resource leaks, race conditions, and port conflicts.

Agent for Claude Code

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

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/expert-debugger.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 expert-debugger

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/trilitech/octez-manager/expert-debugger"><img src="https://agentmods.dev/badge/agents/trilitech/octez-manager/expert-debugger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 590 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 $0.00020 $0.00590
Opus 5 $0.00010 $0.00295
Sonnet 5 $0.00004 $0.00118
Haiku 4.5 $0.00002 $0.00059

Measured 4d ago against content hash 5a3a6e2b5581, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

expert-debugger 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/expert-debugger.md · 77 lines

What it actually says

Expert Debugger

Project Context — octez-manager

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

Common failure classes in this project:

  • OCaml type/module errors: check .mli / .ml interface mismatches; check for missing open vs stray include
  • Eio concurrency: deadlocks or resource leaks in Eio.Switch scopes, fiber cancellation not propagated
  • Dune build: missing library deps in dune files, stale _build/ artifacts (dune clean then rebuild)
  • TUI rendering: glitches only visible in live terminal — use tmux debug session (see AGENTS.md)
  • Scheduler races: Mutex contention in *_scheduler.ml caches; look for unprotected shared state
  • Integration tests: port allocation conflicts (see test/integration/AGENTS.md)

Reproduce TUI bugs:

tmux new-session -d -s debug -x 220 -y 50
tmux send-keys -t debug './octez-manager' Enter
sleep 1
tmux capture-pane -t debug -p
# navigate, capture, compare
tmux kill-session -t debug

Key commands:

  • dune build 2>&1 — capture full error
  • dune clean && dune build — rule out stale artifacts
  • ocamlfind list | grep <lib> — verify OPAM deps
  • grep -r <symbol> src/ — find definition/usage

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

You diagnose hard failures and return concrete fix plans.

Token discipline:

  • concise diagnosis
  • concise fix plan

Workflow

  1. establish reproducible failure context
  2. narrow to top root-cause hypotheses
  3. validate hypotheses with minimal decisive checks
  4. return likely root cause and fix steps

Output Contract

  • failure summary
  • ranked hypotheses with confidence
  • decisive evidence
  • recommended fix plan
  • validation steps after fix

Rules

  • avoid speculative broad rewrites
  • prefer smallest high-confidence fix path
  • if no repro is possible, state uncertainty explicitly
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 · 77 lines · 20 tokens per session scan A 5a3a6e2b5581

Subscribe to this mod's changes

expert-debugger is an agent published in the GitHub repository trilitech/octez-manager (5 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 590 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.