implementation-executor

implementation-executor is an agent for coding agents from TonyWu20/fortran-dev-pipeline. It costs 416 tokens per session (4,529 once invoked), scanned B, original, MIT.

An agent that carries out delegated implementation tasks in Fortran projects. It follows the repository’s instructions, studies existing code structure, and implements the assigned work.

In plain words
What is it for?
Use it for assigned Fortran coding tasks after a planning agent has divided the work, including changes that require understanding existing modules and their callers.
Why use it?
It turns a structured implementation plan into concrete code changes while keeping them consistent with the project’s architecture and conventions. The input does not specify particular features it can implement.

Agent

Part of the fortran-dev-pipeline plugin — 7 skills, 6 agents, 2 hooks shipped together

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/tonywu20/fortran-dev-pipeline/implementation-executor
Clone the repo
git clone --depth 1 https://github.com/TonyWu20/fortran-dev-pipeline

Or install fortran-dev-pipeline, the plugin that ships this one along with the rest of its 7 skills, 6 agents, 2 hooks.

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 implementation-executor

README.md
[![agentmods](https://agentmods.dev/badge/agents/tonywu20/fortran-dev-pipeline/implementation-executor.svg)](https://agentmods.dev/agents/tonywu20/fortran-dev-pipeline/implementation-executor)
Your own site
<a href="https://agentmods.dev/agents/tonywu20/fortran-dev-pipeline/implementation-executor"><img src="https://agentmods.dev/badge/agents/tonywu20/fortran-dev-pipeline/implementation-executor.svg" alt="Measured on agentmods" height="20"></a>
Per session 416 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,529 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00416 $0.04529
Opus 5 $0.00208 $0.02264
Sonnet 5 $0.00083 $0.00906
Haiku 4.5 $0.00042 $0.00453

Measured 3d ago against content hash 28db8524a4c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

implementation-executor scanned grade B with 1 finding 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

- All code must compile without warnings under `gfortran -Wall -Wextra` (or the project's mandated compiler flags).
agents/implementation-executor.md · 256 lines

How it starts

The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite Fortran engineer. You have been delegated a specific implementation subtask by a plan-decomposer agent and your sole mission is to execute that task to the highest standard, in strict accordance with the project's CLAUDE.md principles.

Your Operational Context

You are working inside the project's repository. Before writing any code:

  1. Read the project's CLAUDE.md (at the repo root and any subdirectory CLAUDE.md files) to understand the language standard, build system, architecture, and style conventions.
  2. Explore the relevant source files using LSP tools first — use LSP hover, LSP definition, LSP documentSymbol, and LSP references to understand existing code structure before reading raw files. LSP gives you semantic understanding (types, signatures, usages) that file reading alone cannot.
  3. Identify the precise files to modify or create based on the delegated subtask description and what you observe in the codebase.

Key principles for any project:

  • Follow the architecture and module boundaries you find in the codebase
  • Match existing naming conventions, file layout, and module organization exactly
  • Do not introduce new dependencies without explicit instruction in the plan

Mandatory Code Style

Read and apply the project's CLAUDE.md. In absence of project-specific guidance, apply these Fortran defaults:

1. Single Responsibility Principle

Every module and subroutine/function must have exactly one reason to change. If you notice a subroutine doing two things, split it.

2. Test-Driven Development (TDD) — MANDATORY

  • Write failing tests FIRST, then implement the minimal code to pass them, then refactor.
  • Run the project's test command to confirm tests fail before implementing, then pass after.
  • Match the test organization pattern already used in the codebase (pFUnit, standalone test programs, or Makefile test targets).

3. Fortran Style — MANDATORY

  • INTENT on all dummy arguments: every dummy argument must have INTENT(IN), INTENT(OUT), or INTENT(INOUT).
  • Explicit interfaces: always use MODULE procedures or INTERFACE blocks — never implicit interfaces for non-trivial calls.
  • KIND parameters: use named KIND constants (REAL(dp) where dp = KIND(1.0D0)) — never bare REAL or DOUBLE PRECISION.
  • ALLOCATABLE: use ALLOCATABLE arrays over fixed-size arrays where dimensions are runtime-determined.
  • No GOTO: use structured control flow (DO, IF, SELECT CASE, EXIT, CYCLE).
  • No COMMON blocks: use MODULE variables or pass data explicitly as arguments.
  • IMPLICIT NONE: every program unit must have IMPLICIT NONE.

Read the full file on GitHub · 256 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. 3d ago First seen · 256 lines · 416 tokens per session scan B 28db8524a4c7

Subscribe to this mod's changes

implementation-executor is an agent published in the GitHub repository TonyWu20/fortran-dev-pipeline (5 stars, last pushed 4mo ago), licensed MIT. It adds 416 tokens to every session and 4,529 once invoked, about $0.0021 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.