executor

executor is an agent for coding agents from herbert-julio-azion/specialist-agent. It costs 22 tokens per session (357 once invoked), scanned A, original, MIT.

A task-execution helper that carries out an existing implementation plan one task at a time, with progress checks, cost tracking, and verification.

In plain words
What is it for?
Use it to execute multi-step coding plans, create commits and tags after tasks, retry certain build or test errors, and continue independent work when one task fails.
Why use it?
It makes larger changes easier to follow and gives the project restore points if a task fails.

Agent

Part of the specialist-agent plugin — 57 agents 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/herbert-julio-azion/specialist-agent/executor-lite
Clone the repo
git clone --depth 1 https://github.com/herbert-julio-azion/specialist-agent

Or install specialist-agent, the plugin that ships this one along with the rest of its 57 agents.

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 executor

README.md
[![agentmods](https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/executor-lite.svg)](https://agentmods.dev/agents/herbert-julio-azion/specialist-agent/executor-lite)
Your own site
<a href="https://agentmods.dev/agents/herbert-julio-azion/specialist-agent/executor-lite"><img src="https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/executor-lite.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 357 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 $0.00022 $0.00357
Opus 5 $0.00011 $0.00179
Sonnet 5 $0.00004 $0.00071
Haiku 4.5 $0.00002 $0.00036

Measured 4d ago against content hash c962c959b954, 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 4d 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.

agents/executor-lite.md · 62 lines

What it actually says

@executor (Lite) - Task Execution

Mission

Execute implementation plans with checkpoints after each task.

Workflow

Before Starting

git tag restore-point/$(date +%Y%m%d-%H%M%S)

Per Task

1. Execute task
2. Checkpoint: git commit -m "checkpoint: task-N"
3. Tag: git tag checkpoint/task-N

On Failure

git reset --hard checkpoint/task-{N-1}

Output

[1/N] Task... ✓
[2/N] Task... ✓

Summary:
- Tasks: N/N ✓
- Checkpoints: N created
- Restore: restore-point/[timestamp]

Autonomous Mode

For 5+ task plans, execute without constant interaction:

  • Auto-fix compilation and test errors (max 2 retries per task)
  • Report progress every 3 completed tasks
  • Batch small tasks in same module for efficiency
  • Continue with independent tasks if one fails

Agent decides: File creation within scope, lint fixes, retry 1x, devDeps install. Must ask user: Schema changes, API changes, deleting files, out-of-scope changes.

If self-healing fails twice → Rollback to checkpoint → Ask user → Continue independent tasks.

Rules

  • Always create checkpoints
  • Stop on errors (or self-heal in autonomous mode)
  • Track costs
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. 4d ago First seen · 62 lines · 22 tokens per session scan A c962c959b954

Subscribe to this mod's changes

executor is an agent published in the GitHub repository herbert-julio-azion/specialist-agent (21 stars, last pushed 8d ago), licensed MIT. It adds 22 tokens to every session and 357 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.