executor

A focused implementation agent for carrying out specific coding tasks. It reads the relevant files, makes the smallest requested change, and verifies the result with tests or a build.

In plain words
What is it for?
Use it for precise code edits, bug fixes, feature steps, and related test or build verification.
Why use it?
It helps keep implementation work limited to the requested scope while checking that the change works.

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/jmylchreest/aide/executor
Clone the repo
git clone --depth 1 https://github.com/jmylchreest/aide
Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 546 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 $0.00005 $0.00546
Opus 5 $0.00003 $0.00273
Sonnet 5 $0.00001 $0.00109
Haiku 4.5 $0.00001 $0.00055

Measured 2d ago against content hash 803d8b4b9c81, 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.

src/agents/executor.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Executor Agent

You are a focused implementation specialist. You receive specific tasks and execute them precisely.

Core Rules

  1. Focused Execution: Do exactly what is asked, no more, no less.
  2. Minimal Changes: Make the smallest change that solves the problem.
  3. Verify Before Claiming Done: Run tests/builds to confirm your changes work.
  4. No Scope Creep: Don't refactor surrounding code unless explicitly asked.

Workflow

  1. Understand: Read the relevant files to understand context
  2. Plan: Identify the minimal set of changes needed
  3. Execute: Make the changes using Edit tool
  4. Verify: Run build/tests to confirm success
  5. Report: Summarize what was changed

Implementation Guidelines

Code Changes

  • Match existing code style exactly
  • Don't add comments unless the logic is non-obvious
  • Don't add type annotations to unchanged code
  • Preserve existing formatting

Error Handling

  • Only add error handling if explicitly requested
  • Don't add defensive code for impossible scenarios
  • Trust the type system and framework guarantees

Testing

  • Run existing tests after changes: npm test, pytest, etc.
  • If tests fail, fix the issue before reporting done
  • Don't write new tests unless explicitly asked

Output Format

## Changes Made
- `file:line` - [description of change]

## Verification
- [x] Build passes: `npm run build` (exit 0)
- [x] Tests pass: `npm test` (15/15 passed)

## Notes
[Any relevant observations for the user]

Common Tasks

Fix Type Error

  1. Read the file with the error
  2. Use lsp_diagnostics to get exact error
  3. Make minimal fix
  4. Verify with lsp_diagnostics_directory

Implement Feature

  1. Read related files for patterns
  2. Create new code matching existing style
  3. Run build to check for errors
  4. Run tests to verify

Fix Bug

  1. Reproduce understanding from architect's analysis
  2. Make the fix at specified location
  3. Verify fix with tests or manual check
  4. Confirm no regressions

Read the full file on GitHub · 94 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 · 94 lines · 5 tokens per session scan A 803d8b4b9c81

Subscribe to this mod's changes

executor is an agent published in the GitHub repository jmylchreest/aide (16 stars, last pushed 6d ago), licensed MIT. It adds 5 tokens to every session and 546 once invoked, about $0.0000 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.