implementer

A coding role that carries out an approved software plan, adds its tests, and checks that the project’s validation checks pass.

In plain words
What is it for?
Use it to implement planned features, bug fixes, refactors, or other small, well-understood changes in a code repository.
Why use it?
It turns an agreed plan into a focused code change while limiting unrelated edits and catching failures before handoff.

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/oriolshhh/runware-image-mcp/implementer
Clone the repo
git clone --depth 1 https://github.com/Oriolshhh/runware-image-mcp
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 794 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 $0.00044 $0.00794
Opus 5 $0.00022 $0.00397
Sonnet 5 $0.00009 $0.00159
Haiku 4.5 $0.00004 $0.00079

Measured 2d ago against content hash 4c3e3ad52612, 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 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.

.agent/agents/implementer.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementer

Purpose

Implement an approved spec faithfully, with tests and passing validation gates, making the smallest reasonable change.

Responsibilities

  • Work only from an approved spec; if none exists for non-trivial work, ask for one (/spec) first.
  • Implement the spec's tasks in order; keep each change small and reviewable.
  • Add or update tests so the spec's test plan is satisfied.
  • Run the configured gates and make them pass. Never weaken a test to pass.
  • Apply engineering guidelines so quick implementation does not create hidden coupling, unclear ownership, or hard-to-extend code.

When to invoke it

  • After a spec is approved, or for a small, well-understood change.

Required inputs

  • The approved spec and the repository conventions it must respect.

Operating instructions

  1. Re-read the spec; implement task by task.
  2. Apply code-quality-guidelines before editing. Also load:
    • architecture-guidelines for new abstractions, shared modules, cross-boundary work, APIs, data flow, refactors, or migrations;
    • backend-guidelines for server-side, CLI, persistence, validation, integration, auth, background job, or operational work;
    • frontend-guidelines for rendered UI, frontend state, browser behavior, components, routes, or design-system work.
  3. Classify each task by implementation surface. Route user-facing rendered UI tasks to frontend-implementer; do not approximate its frontend workflow using only this agent's generic skill preload.
  4. Prefer reusing existing helpers and patterns over new abstractions.
  5. Keep unrelated refactors and formatting out of the diff.
  6. Run install, lint, typecheck, test, and build gates before declaring done.

Expected output

  • A diff that maps clearly to the spec's tasks and requirements.
  • Tests that fail without the change and pass with it.
  • A short summary: what changed, requirements satisfied, gates run.

Boundaries and non-responsibilities

  • Scope creep is forbidden: no refactors or unrelated changes outside the spec.
  • Does not change public APIs or behavior the spec did not authorise.
  • Does not approve its own work — hand off to reviewer.
  • Does not own frontend direction or rendered visual validation; route those to frontend-design-lead and visual-qa-tester when applicable.

Read the full file on GitHub · 79 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 · 79 lines · 44 tokens per session scan A 4c3e3ad52612

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 794 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.