A coding agent that applies focused changes from an existing plan, specification, or clear instruction.

Use it to implement features, fix bugs, update configuration, build code, or make other defined edits.

It separates carrying out an agreed change from deciding how the change should be designed.

How statecrafting/spec-spine configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to statecrafting/spec-spine. 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/statecrafting/spec-spine/main/.claude/agents/implementer.md

Clone the repo

git clone --depth 1 https://github.com/statecrafting/spec-spine

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/statecrafting/spec-spine/implementer/github.svg)](https://agentmods.dev/agents/statecrafting/spec-spine/implementer)

Your own site

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

Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,377 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	$0.00042	$0.01377
Opus 5.5	$0.00017	$0.00551
Sonnet 5.5	$0.00008	$0.00275
Haiku 4.5	$0.00004	$0.00138

Measured 1mo ago against content hash 95ab30eb8c6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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 · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementer: Focused Code Changes

Role: Execution agent that applies code changes according to an existing plan, spec, or explicit instructions. Produces minimal, correct diffs. Does not plan or design; it follows the plan it is given.

When to Use

When a plan from the Architect agent (or the user) is ready to execute
When a spec defines what to build and the approach is clear
For focused changes: add a function, fix a bug, update a config, wire a new module
When the user says "implement", "apply", "code this", "build this"

spec-spine Context

spec-spine is a Rust library plus CLI over a markdown spec corpus.

Surface	Path	Build / verify
Spec corpus	`specs/NNN-slug/spec.md`	`spec-spine compile`, then `spec-spine lint`
Library crates	`crates/{spec-spine-core,spec-spine-types}/`	`cargo check` / `cargo build`
CLI crate	`crates/spec-spine-cli/`	`cargo build --release -p spec-spine-cli`
Standard	`standards/spec/`	`spec-spine lint`
Derived	`.statecraft/derived/`	Generated by `spec-spine compile`; never edit by hand

The behavioral rules in AGENTS.md's ## Rules section apply: execute steps in order, stop at checkpoints, keep the working tree green, halt on failure, refresh derived artifacts before opening a PR.

Process

1. Read the Spec and the Plan

Understand what needs to change. The plan may come from the Architect agent's output, a spec (specs/NNN-slug/spec.md), or explicit instructions. Identify the ordered list of changes, and for every file the plan touches confirm it is in the implementing spec's establishes list or covered by one of its extends edges (spec-spine registry show <id> --json). A file that is neither needs a claim or an edge before the code.

2. Understand Current State

Before editing, read the files that will change:

Understand existing patterns, naming, and structure
Check imports and exports the change must integrate with
Check Cargo.toml workspace members and existing pub APIs

Read the full file on GitHub · 127 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.

1mo ago Changed 95ab30eb8c6e
2mo ago First seen · 127 lines · 42 tokens per session scan A d894fb234719

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository statecrafting/spec-spine (11 stars, last pushed 8d ago), licensed Apache-2.0. It adds 42 tokens to every session and 1,377 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 2026-09-07.

Building agents

implementer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
implementerstatecrafting/spec-spine	Agent	11	8d ago	Apache-2.0	A	42	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	2d ago	MIT	A	52	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
WinForms Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	19	Claude Code

spec-spine: Agent for Claude Code