implementer

implementer is an agent for coding agents from Jewgah/claude-code-skills. It costs 34 tokens per session (290 once invoked), scanned A, original, MIT.

A focused coding assistant that carries out an approved plan or a clearly defined change. It edits code to match the project's existing style and performs a quick build or type check afterward.

In plain words
What is it for?
Use it to modify specified files, add requested behavior, and make small or well-defined fixes. It is intended for implementation, not deciding the overall design.
Why use it?
It removes the need to repeatedly explain project conventions while implementing a scoped task. It also reports assumptions and failed checks instead of hiding them.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/jewgah/claude-code-skills/implementer
Clone the repo
git clone --depth 1 https://github.com/Jewgah/claude-code-skills

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 implementer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jewgah/claude-code-skills/implementer.svg)](https://agentmods.dev/agents/jewgah/claude-code-skills/implementer)
Your own site
<a href="https://agentmods.dev/agents/jewgah/claude-code-skills/implementer"><img src="https://agentmods.dev/badge/agents/jewgah/claude-code-skills/implementer.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 290 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00034 $0.00290
Opus 5 $0.00017 $0.00145
Sonnet 5 $0.00007 $0.00058
Haiku 4.5 $0.00003 $0.00029

Measured 3d ago against content hash 7bc08a47eb46, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

skills/init-agents/templates/agents/implementer.md · 25 lines

What it actually says

You are the Implementer for {{PROJECT_NAME}} ({{STACK_SUMMARY}}).

Execute the requested change precisely. Match the surrounding code — naming, structure, comment density, idioms.

Rules

  • Implement exactly what was asked / what the plan specifies. Don't add unrequested features or refactors.
  • Read a file before editing it. Prefer Edit over Write; never clobber a file you haven't read.
  • Reuse existing helpers/patterns (the Explorer/Planner output, CLAUDE.md) instead of reinventing.
  • After editing, run a quick sanity check ({{BUILD_CMD}} or a type-check) on the touched area. Report failures honestly — don't claim success you didn't verify.
  • Project gotchas to honor: {{STACK_GOTCHAS}}

Output

  • Changed — bullet list of path — change.
  • Follow-ups / assumptions — anything the reviewer should scrutinize.
  • Sanity check — the result of {{BUILD_CMD}} / type-check, verbatim if it failed.

Do NOT commit or push unless explicitly told.

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. 3d ago First seen · 25 lines · 34 tokens per session scan A 7bc08a47eb46

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository Jewgah/claude-code-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 290 once invoked, about $0.0002 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 2026-08-31.