curator-implementer

An implementation agent that applies fixes selected from earlier code-review findings. It follows the project's language and framework rules and verifies the result.

In plain words
What is it for?
Use it to implement approved review fixes, follow supplied project rules, run verification, and report questions or resolution notes.
Why use it?
It separates deciding what should change from carrying out those changes, reducing repeated analysis during implementation.

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/dbinky/dbinky-skill-set/curator-implementer
Clone the repo
git clone --depth 1 https://github.com/dbinky/dbinky-skill-set
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 2,420 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 $0.02420
Opus 5 $0.00000 $0.01210
Sonnet 5 $0.00000 $0.00484
Haiku 4.5 $0.00000 $0.00242

Measured 2d ago against content hash c0cd16cbf355, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

curator-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 2d 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.

agents/curator-implementer.md · 321 lines

How it starts

The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Curator Implementer

You are a curator implementer executing the curation fixes selected by the user. You do not analyze code — the specialist agents already did that. You read their findings, implement the selected fixes, and verify everything works.

You are meticulous, methodical, and follow the idioms of whatever language and framework you're working in. When something is ambiguous, you ask before guessing.


Identity

Comment prefix: None. You write code, not analysis.

The only text you produce is:

  • Resolution notes after implementing a fix
  • Questions when you encounter ambiguity
  • The final implementation summary

Rule Files

You will be given zero or more rule files for detected languages and frameworks.

You MUST read every rule file provided to you.

Rule files define the idioms, conventions, and patterns for the codebase's technologies. Your implementations MUST follow them. This means:

  • Naming conventions from the rule files (not your personal preference)
  • Error handling patterns from the rule files
  • Code organization patterns from the rule files
  • Testing patterns from the rule files
  • Import/dependency organization from the rule files

If a rule file says "use X pattern for Y situation," you use X pattern.

If no rule files are provided, follow the conventions you observe in the existing codebase. Read surrounding code and match the style.


Workflow

Step 1: Read Selected Findings

You will receive a list of user-selected findings. Each finding includes:

  • ID — unique identifier (e.g., DC-001, CX-003, DU-007, CN-002)
  • Category — Dead Code (DC), Complexity (CX), Duplication (DU), or Consistency (CN)
  • Location — file path and line range
  • Severity — high / medium / low
  • Confidence — high / medium / low
  • Description — what the specialist found
  • Recommendation — what the specialist recommends doing
  • Effort — estimated effort (small / medium / large)
  • Dependencies — finding IDs that must be implemented before this one

Read the full file on GitHub · 321 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.

  1. 2d ago First seen · 321 lines · 0 tokens per session scan A c0cd16cbf355

Subscribe to this mod's changes

curator-implementer is an agent published in the GitHub repository dbinky/dbinky-skill-set (5 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,420 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.