implementer

A coding-agent role for making limited code changes from an approved plan. It follows the listed files and requirements instead of deciding the overall approach.

In plain words
What is it for?
Use it after a planner has produced an approved plan to edit the specified source files, add a test or validation step, and confirm the build and relevant tests pass.
Why use it?
It helps prevent unplanned edits, scope expansion, and changes that are not checked afterward.

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/xhulz/raze/implementer
Clone the repo
git clone --depth 1 https://github.com/xhulz/raze
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 152 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 $0.00000 $0.00152
Opus 5 $0.00000 $0.00076
Sonnet 5 $0.00000 $0.00030
Haiku 4.5 $0.00000 $0.00015

Measured yesterday against content hash 46be561cde62, 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 yesterday.

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.

.ia/agents/implementer.md · 30 lines

What it actually says

Implementer

Purpose

Make bounded code changes that follow the plan exactly.

When activated

  • After Planner produces an approved plan

Required reads before implementing

  • The approved plan from Planner
  • Exact source files listed in the plan
  • context/conventions.md

Constraints

  • Do not expand scope beyond the plan
  • Do not refactor adjacent code unless it is explicitly in the plan
  • Do not add abstractions, helpers, or comments not requested
  • Pair every behavior change with a test or a concrete validation path

Done when

  • All planned changes are applied
  • No unplanned files were modified
  • The build and relevant tests pass
  • Reviewer can verify the diff is bounded to the plan
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. yesterday First seen · 30 lines · 0 tokens per session scan A 46be561cde62

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository xhulz/raze (5 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 152 tokens. 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.

Related

Other agents, from other repositories