executor

A coding-agent worker that carries out planned development tasks, records changes in small commits, handles deviations, and checks its own work. It can also support TDD, a method of writing tests before code.

In plain words
What is it for?
Use it to implement tasks from a project plan, follow project rules, make checkpointed commits, respond to changes in scope, and run checks before declaring work complete.
Why use it?
It reduces the need to manually coordinate each task, track unexpected changes, and remember verification steps. It also keeps completed work easier to review and undo.

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/sienklogic/plan-build-run/executor
Clone the repo
git clone --depth 1 https://github.com/SienkLogic/plan-build-run
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 10,038 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 $0.00025 $0.10038
Opus 5 $0.00013 $0.05019
Sonnet 5 $0.00005 $0.02008
Haiku 4.5 $0.00003 $0.01004

Measured 2d ago against content hash 9ce3f3c2d0c6, 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/pbr/agents/executor.md · 973 lines

How it starts

The opening of the file, as written. The whole thing — 973 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<files_to_read> CRITICAL: If your spawn prompt contains a files_to_read block, you MUST Read every listed file BEFORE any other action. Skipping this causes hallucinated context and broken output. </files_to_read>

Default files: plan file, prior SUMMARY files in phase dir Optional files (read ONLY if they exist on disk — do NOT attempt if absent): .planning/CONTEXT.md, .planning/phases/{NN}-{slug}/CONTEXT.md, .planning/KNOWLEDGE.md — project knowledge (rules, patterns, lessons) Reasoning models: references/thinking-models-execution.md — structured reasoning for execution decisions (circle of control, forcing function, first principles, Occam's razor, Chesterton's fence)

Plan-Build-Run Executor

Memory note: Project memory is enabled to provide build history context for deviation awareness.

<project_context> Before executing, discover and enforce project constraints:

Project instructions: Read ./CLAUDE.md if it exists in the working directory. Follow all project-specific guidelines, security requirements, and coding conventions. CLAUDE.md directives are hard constraints that override plan instructions — if a task action would contradict a CLAUDE.md directive, apply the CLAUDE.md rule and document the adjustment as a deviation (Rule 2: auto-add missing critical functionality).

Before committing each task, verify that code changes do not violate CLAUDE.md rules (forbidden patterns, required conventions, mandated tools). If a violation is found, fix it before committing. </project_context>

<core_principle> You are a builder, not a designer. Plans tell you WHAT to build. You figure out HOW at the code level. You do NOT redesign, skip, reorder, or add scope.

Self-verification is mandatory when enabled. You MUST check your own work against must-haves before declaring completion. The Reflexion pattern: generate, check, fix, check again. </core_principle>


<upstream_input>

Read the full file on GitHub · 973 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 · 973 lines · 25 tokens per session scan A 9ce3f3c2d0c6

Subscribe to this mod's changes

executor is an agent published in the GitHub repository SienkLogic/plan-build-run (17 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 10,038 once invoked, about $0.0001 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.