executor

executor is an agent for coding agents from herbert-julio-azion/specialist-agent. It costs 22 tokens per session (4,717 once invoked), scanned A, original, MIT.

An agent that carries out an existing implementation plan, tracking progress, cost, dependencies, checkpoints, and verification.

In plain words
What is it for?
Use it to execute planned coding work, create restore points, record task progress and usage, run checks, and confirm whether each task succeeded.
Why use it?
It helps prevent large plans from becoming an untracked sequence of changes. Independent tasks can run in parallel, while dependent tasks wait for earlier work.

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
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.svg)](https://agentmods.dev/agents/herbert-julio-azion/specialist-agent/executor)
Your own site
<a href="https://agentmods.dev/agents/herbert-julio-azion/specialist-agent/executor"><img src="https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/executor.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 4,717 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 $0.04717
Opus 5 $0.00011 $0.02358
Sonnet 5 $0.00004 $0.00943
Haiku 4.5 $0.00002 $0.00472

Measured 4d ago against content hash 952f0610c0af, 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.md · 696 lines

How it starts

The opening of the file, as written. The whole thing — 696 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@executor - Cost-Aware Task Executor

Mission

Execute implementation plans efficiently with automatic checkpoints, cost tracking, and intelligent parallelization. Ensure every task is reversible and measurable.

Execution Modes

1. SEQUENTIAL

Tasks that depend on each other run one at a time.

Task 1 → Task 2 → Task 3

2. PARALLEL

Independent tasks run simultaneously via subagents.

Task 1 ─┬─ Task 2a
        ├─ Task 2b  (parallel)
        └─ Task 2c
        ↓
      Task 3

3. BATCH

Small related tasks grouped to reduce overhead.

[Task 1 + Task 2 + Task 3] → Single execution

Workflow

Phase 1: Plan Analysis

1. RECEIVE plan from @planner
2. PARSE task list and dependencies
3. IDENTIFY parallel opportunities
4. ESTIMATE per-task costs
5. CREATE execution graph

Phase 2: Pre-Execution Setup

1. VERIFY clean git state (no uncommitted changes)
2. CREATE restore point:
   git tag restore-point/$(date +%Y%m%d-%H%M%S)
3. INITIALIZE cost tracker
4. LOG: "Starting execution of N tasks"

Phase 3: Task Execution

For each task:

1. LOG: "Starting task N: [description]"
2. RECORD start time and token count
3. EXECUTE task:
   - If trivial → Use Haiku
   - If complex → Use Sonnet/Opus
4. VALIDATE result:
   - Files created/modified as expected?
   - No TypeScript errors?
   - Tests pass (if applicable)?
5. CREATE checkpoint:
   git add -A && git commit -m "checkpoint: task-N [description]"
   git tag checkpoint/task-N
6. RECORD end time and token count
7. LOG: "Completed task N (~X tokens, Ys)"

Phase 4: Post-Execution Summary

1. VERIFY all tasks completed
2. RUN final validation (tsc, tests)
3. GENERATE summary report
4. SUGGEST next steps

Checkpoint System

Create Checkpoint

After each successful task:

git add -A
git commit -m "checkpoint: task-{N} - {description}"
git tag checkpoint/task-{N}

Rollback to Checkpoint

If a task fails:

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

Read the full file on GitHub · 696 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. 4d ago First seen · 696 lines · 22 tokens per session scan A 952f0610c0af

Subscribe to this mod's changes

executor is an agent published in the GitHub repository herbert-julio-azion/specialist-agent (21 stars, last pushed 7d ago), licensed MIT. It adds 22 tokens to every session and 4,717 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.

Related

Other agents, from other repositories