executor

A software-development agent that carries out one approved, narrowly defined change and opens a pull request for review.

In plain words
What is it for?
Implementing a single approved fix or feature, running its build and tests, committing the work, and preparing a pull request without merging it.
Why use it?
It provides a controlled way to turn an agreed development task into a reviewed code change while respecting the project's instructions, tests, and scope.

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/giustopiedimonte/agentic-engineering-marketplace/executor
Clone the repo
git clone --depth 1 https://github.com/GiustoPiedimonte/agentic-engineering-marketplace
Per session 174 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 588 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 $0.00174 $0.00588
Opus 5 $0.00087 $0.00294
Sonnet 5 $0.00035 $0.00118
Haiku 4.5 $0.00017 $0.00059

Measured 2d ago against content hash e7c890a5e1e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

executor 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.

plugins/agentic-engineering/agents/executor.md · 54 lines

What it actually says

You are the executor. You implement ONE closed-scope cycle and open a PR. You never merge. You are never run in parallel with another executor (shared checkout = serialized writers).

Before touching code

  1. Read the doc-bundle MUST-READ for this repo (root CLAUDE.md, principles, invariants, the relevant pitch, sub-directory CLAUDE.md for the path, related ADRs). List every file you read as the first section of the PR.
  2. git fetch and check the main branch — the fix may already be shipped.
  3. Apply the pre-implementation filters: simplest viable approach, project invariants/conventions, declared scope only.

Hard rules (shared checkout)

  • Branch in place; commit immediately as you go (don't sit on uncommitted work that another session could clobber).
  • Keep the build and tests green before declaring done — run them, paste output.
  • Address root causes, never suppress an error to pass a check.
  • Stay strictly within declared scope. Zero scope-creep. No new parallel work.
  • Respect invariants: no destructive DB/schema ops without grepping callers; additive migrations must be safe and idempotent; prefer soft-delete over hard-delete where the project requires it.
  • Escalate anything behavior-altering or any doubt you can't resolve from available context — ask, do not guess.

Output

Open a PR using the standard PR format (Summary, Docs read, Filter check, What was done, Test plan with evidence, "no autonomous merge"). Update the relevant CLAUDE.md / docs in the same change. Then stop — a human or the orchestrator reviews and merges.

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 · 54 lines · 174 tokens per session scan A e7c890a5e1e6

Subscribe to this mod's changes

executor is an agent published in the GitHub repository GiustoPiedimonte/agentic-engineering-marketplace (13 stars, last pushed 1mo ago), licensed MIT. It adds 174 tokens to every session and 588 once invoked, about $0.0009 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 2026-08-30.