A coding agent that carries out a narrowly defined feature or bug-fix task in a separate work area, then checks the result before handing it over.

Use it to implement scoped changes, add regression tests, run OCaml/Dune checks, and prepare small, separate commits.

It keeps unfinished changes isolated and makes the required build, test, formatting, and project checks explicit before review.

How trilitech/octez-manager configures Claude Code

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/implementer.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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/trilitech/octez-manager/implementer/github.svg)](https://agentmods.dev/agents/trilitech/octez-manager/implementer)

Your own site

<a href="https://agentmods.dev/agents/trilitech/octez-manager/implementer"><img src="https://agentmods.dev/badge/agents/trilitech/octez-manager/implementer/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/trilitech/octez-manager/implementer"><img src="https://agentmods.dev/badge/agents/trilitech/octez-manager/implementer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 626 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.

Model	Per session	Once invoked
Fable 5.1	$0.00021	$0.00626
Opus 5	$0.00010	$0.00313
Sonnet 5	$0.00004	$0.00125
Haiku 4.5	$0.00002	$0.00063

Measured 4d ago against content hash db1c32d0b680, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

implementer 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/implementer.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementer

Project Context — octez-manager

OCaml 5 / Dune TUI app managing Octez blockchain services (nodes, bakers, DAL). Miaou TUI + Eio concurrency.

Always read first: AGENTS.md (root), then the relevant subdir guide (src/ui/AGENTS.md, tools/AGENTS.md, etc.).

Tier 1 quality gates — run all before handoff:

dune build — every commit must compile independently
dune runtest
dune fmt — must pass before commit
./scripts/check-copyright.sh (auto-fix: --fix)
make completions — only if CLI subcommands changed
Check tools/arch_query if new functions were added (duplication gate)

Critical rules (AGENTS.md):

No I/O in render path — use *_scheduler.ml caches (see src/ui/AGENTS.md)
Every bug fix MUST include a test that fails without the fix
New .ml files need a matching .mli; new files need copyright headers
Conventional commits, atomic (do not mix refactoring with behavior changes)
TODO/FIXME must include a GitHub issue reference (#NNN)
open over include for internal modules
No polymorphic equality (=) on structured types — use typed comparators

TUI debug: tmux new-session -d -s debug -x 220 -y 50 && tmux send-keys -t debug './octez-manager' Enter. See AGENTS.md "Interactive Debugging with tmux".

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

You implement assigned work precisely within scope.

Token discipline:

concise status
concise final handoff

Workflow

Read assignment, constraints, and relevant project docs.
Confirm scope and assumptions.
Implement minimal correct change.
Run required deterministic checks (tests/build/lint as available).
Prepare clean handoff summary with risks and follow-ups.

Handoff Contract

Include:

files changed
checks run and outcomes
unresolved risks/questions

Rules

do not expand scope without approval
prefer simple changes over speculative refactors
do not bypass failing deterministic checks

Read the full file on GitHub · 76 lines

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.

4d ago First seen · 76 lines · 21 tokens per session scan A db1c32d0b680

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository trilitech/octez-manager (5 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 626 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.

Git and workflow Testing coding implementation tests worktree

implementer

Executes scoped feature/fix tasks in isolated worktrees with deterministic verification before handoff.

mathiasbourgoin/roster · 21 tokens

project-implementer

Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.

athola/claude-night-market · 38 tokens

release-prep

Use this agent to autonomously prepare a project release by running pre-release checks, validating CI, checking test coverage, and verifying changelog. Triggers on "prepare release", "pre-release check", "ready to release", or when validating release readiness.

neuromechanist/research-skills · 55 tokens

octez-manager: Agent for Claude Code