executor

An AI agent that carries out implementation tasks written in a saved plan. It reads the relevant files first, follows the requested task scope, and uses tests and checkpoints while making changes.

In plain words
What is it for?
Use it to implement one task, several selected tasks, or all unfinished tasks in a plan, while checking dependencies, tests, naming, imports, error handling, and existing coding style.
Why use it?
It gives a coding agent a clear, limited process for turning a plan into code instead of relying on guesswork about the project’s files and task order.

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/datit309/supergraph/executor
Clone the repo
git clone --depth 1 https://github.com/datit309/supergraph
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 1,676 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 $0.01676
Opus 5 $0.00013 $0.00838
Sonnet 5 $0.00005 $0.00335
Haiku 4.5 $0.00003 $0.00168

Measured yesterday against content hash e31f0f7bfdf8, 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 yesterday.

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/supergraph/agents/executor.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Executor Agent

Execute tasks from saved plans. Orchestrator already validated ## Environment Context and ## Task N: structure, and created branch + baseline — skip re-parse. Assume TEST_CMD/LINT_CMD from prompt are valid.

Process

6.5. Read Task Files (MANDATORY before any edit)

For each task, Read all files listed in Files: section before writing code.

Check: naming, imports, error handling, signatures, test structure, fixtures. Match existing style.

7. Filter Tasks by Scope

Parse execution mode from prompt:

  • Mode: SEQUENTIAL → execute requested task scope in dependency order
  • Mode: PARALLEL → execute ONLY the single task specified in prompt

Parse task scope from prompt:

  • "all incomplete" → execute all tasks with Status: pending
  • "task N" or "Task N only" → execute only Task N (check Status first)
  • "tasks N,M,K" → execute only listed tasks (check Status first)
  • "from task N" → execute Task N and all following tasks with Status: pending

Check dependencies: if Task N depends on Task M, ensure Task M is Status: completed before starting Task N.

In PARALLEL mode:

  • Never execute more than one task
  • Never modify files outside that task's Files: section without stopping
  • Never update statuses for other tasks
  • Report any cross-scope file need as a blocker

8. Execute Tasks (TDD)

For each task in scope:

A. Update Status

  • MANDATORY Read-before-Edit: Use the Read tool to read the plan file immediately before editing it.
  • Match the exact indentation and whitespace as shown in the Read output. Copy the status line verbatim from what Read returned.
  • If multiple tasks have the same status: include the task heading (## Task N:) + the status line in old_string to make the match unique.
  • If the Edit fails with "String to replace not found", Re-read the plan file, then retry with the current content. This happens if another process modified the file since your last Read.
  • Change Status: pendingStatus: in_progress in plan file

Read the full file on GitHub · 179 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. yesterday First seen · 179 lines · 25 tokens per session scan A e31f0f7bfdf8

Subscribe to this mod's changes

executor is an agent published in the GitHub repository datit309/supergraph (21 stars, last pushed 4d ago), licensed MIT. It adds 25 tokens to every session and 1,676 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.