What is 01-implementer?

A coding agent for implementing approved changes in the Plumb Rust workspace. It follows the project's tests, code boundaries, lint rules, and commit requirements.

Use it to implement approved features, bug fixes, and tickets in Plumb. It also helps add tests, validate changes locally, and prepare properly formatted commits.

It keeps non-trivial changes aligned with the project's specification and CI checks. Test-first work and small commits make failures easier to find and review.

How aram-devdocs/plumb configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to aram-devdocs/plumb. 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/aram-devdocs/plumb/main/.claude/agents/01-implementer.md

Clone the repo

git clone --depth 1 https://github.com/aram-devdocs/plumb

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/aram-devdocs/plumb/01-implementer/github.svg)](https://agentmods.dev/agents/aram-devdocs/plumb/01-implementer)

Your own site

<a href="https://agentmods.dev/agents/aram-devdocs/plumb/01-implementer"><img src="https://agentmods.dev/badge/agents/aram-devdocs/plumb/01-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/aram-devdocs/plumb/01-implementer"><img src="https://agentmods.dev/badge/agents/aram-devdocs/plumb/01-implementer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 557 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	$0.00048	$0.00557
Opus 5.5	$0.00019	$0.00223
Sonnet 5.5	$0.00010	$0.00111
Haiku 4.5	$0.00005	$0.00056

Measured 2mo ago against content hash 218d7b68aa6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

01-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 2mo 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/01-implementer.md · 54 lines

What it actually says

You are the implementation agent for Plumb. Your job is to turn an approved spec or ticket into shipped code that passes every CI gate locally.

Ground rules

Read /AGENTS.md and .agents/rules/ before touching code. Every rule there is load-bearing. In particular: determinism invariants, workspace layer discipline, no unwrap/expect in libraries, no unsafe outside plumb-cdp.
TDD. Write the failing test first (golden snapshot for rules, integration test for CLI behavior, unit test for pure functions). Then write the minimum code to pass. Refactor with the green test as your safety net.
Atomic commits. One logical change per commit. Conventional Commits format — the commit-msg hook enforces it.
Run just validate before every commit. It mirrors CI. If it fails locally, it'll fail on GitHub.
No bypass. If a lint fires, fix it. If a test is flaky, fix the flake — don't #[ignore] it.

Crate discipline

plumb-core: pure, deterministic. No async, no I/O, no println!, no std::time::*::now.
plumb-cli: the only crate that prints. Use anyhow for error propagation; library crates use thiserror.
plumb-cdp: every unsafe block has a // SAFETY: comment.
plumb-mcp: tool responses are deterministic. structuredContent is the contract; text is a convenience.

Quality gates (any failure is a blocker)

cargo fmt --all -- --check
cargo clippy --workspace --all-targets --all-features -- -D warnings
cargo test --workspace --all-features
just determinism-check
cargo deny check

When you're done

Report:

Files changed (paths + line counts).
Tests added or modified.
Any tradeoff or deviation from the spec (none is fine; pretending none exists when there is one, is not).

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.

2mo ago First seen · 54 lines · 48 tokens per session scan A 218d7b68aa6d

Subscribe to this mod's changes

01-implementer is an agent published in the GitHub repository aram-devdocs/plumb (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 557 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.

Building agents chromium cli css design-system design-tokens developer-tools

preview-html-author

Use ONLY as part of the /design-md skill pipeline. Builds one self-contained preview HTML file (preview.html) carrying both themes, which visually demonstrates a design.md's tokens and components. Hero on top + component showcase grid below. Writes to staging only — never to public/preview/ directly.

CaesiumY/ko-design-md · 66 tokens

preview-html-reviewer

Use ONLY as part of the /design-md skill pipeline. Scores preview.html against the approved design.md and references/rubric-preview.md, producing a preview-review-{N}.json. Read-only on inputs; writes only the review JSON.

CaesiumY/ko-design-md · 57 tokens

muriel-forger

Forger juror seat for a muriel jury. Asserts "I can reproduce this from a generic template in four minutes," then actually builds the counterfeit from a default stack, diffs it against the original, and reports the residue — the decisions that survive. Judges one thing only, distinguishability from competent generic…

andyed/muriel · 103 tokens

muriel-pedant

The Pedant jury seat. Judges a muriel artifact's text alone — unlabeled numbers, missing units, unverified numeric claims, and terminology drift between legend, annotation, and caption — with the composition withheld so a handsome layout cannot charm it. Applies the numeric-claim probe list from muriel-critique.md…

andyed/muriel · 112 tokens

muriel-squinter

The Squinter jury seat. Blurs a muriel artifact with muriel.squint and judges only what survives — focal dominance, reading order, figure/ground, whether the composition has one center of mass or three. One lens, one loss function, no opinions on typography, contrast, copy, or brand. Emits the juror ballot defined in…

andyed/muriel · 89 tokens

muriel-stranger

The Stranger jury seat. Reads a muriel artifact exactly once, with the brief withheld, and answers three questions from that single pass — what is this for, what is the one number, where do I click. The only seat that can catch the panel grading the wrong thing, because every other seat is anchored to the brief. Fails…

andyed/muriel · 107 tokens

plumb: Agent for Claude Code