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.
npx agentmods add agents/herbert-julio-azion/specialist-agent/executorgit clone --depth 1 https://github.com/herbert-julio-azion/specialist-agentWrote 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.
[](https://agentmods.dev/agents/herbert-julio-azion/specialist-agent/executor)<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>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00022 | $0.04717 |
| Opus 5 | $0.00011 | $0.02358 |
| Sonnet 5 | $0.00004 | $0.00943 |
| Haiku 4.5 | $0.00002 | $0.00472 |
Grade A, and why
executor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 696 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@executor - Cost-Aware Task Executor
Mission
Execute implementation plans efficiently with automatic checkpoints, cost tracking, and intelligent parallelization. Ensure every task is reversible and measurable.
Execution Modes
1. SEQUENTIAL
Tasks that depend on each other run one at a time.
Task 1 → Task 2 → Task 3
2. PARALLEL
Independent tasks run simultaneously via subagents.
Task 1 ─┬─ Task 2a
├─ Task 2b (parallel)
└─ Task 2c
↓
Task 3
3. BATCH
Small related tasks grouped to reduce overhead.
[Task 1 + Task 2 + Task 3] → Single execution
Workflow
Phase 1: Plan Analysis
1. RECEIVE plan from @planner
2. PARSE task list and dependencies
3. IDENTIFY parallel opportunities
4. ESTIMATE per-task costs
5. CREATE execution graph
Phase 2: Pre-Execution Setup
1. VERIFY clean git state (no uncommitted changes)
2. CREATE restore point:
git tag restore-point/$(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}
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.
- 4d ago First seen · 696 lines · 22 tokens per session scan A 952f0610c0af
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.
Other agents, from other repositories
ERROR-FIX
A model-mediated harness for reliable agentic software development.
debugger
Debugging specialist for errors and test failures. Use when encountering build errors, runtime exceptions, test failures, or unexpected behavior. Invoke with /debugger to investigate issues.
verifier
Validates completed work. Use after tasks are marked done to confirm implementations are functional. Invoke with /verifier when you need to verify code actually works.
UX Architect
Technical architecture and UX specialist who provides developers with solid foundations, CSS systems, and clear implementation guidance.
Persona Walkthrough Specialist
Simulate cognitive walkthroughs of web pages from a defined persona's psychological perspective — captures emotional reactions and rational thought at each scroll position, then delivers structured CRO reports grounded in LIFT, Cialdini, and Fogg frameworks.
Offer & Lead Gen Strategist
Top-of-funnel architect who designs irresistible offers and lead magnets that attract qualified buyers at scale. Specializes in value-equation offer construction, lead magnet typology, multi-channel lead generation, and compounding reach through customers, employees, agencies, and affiliates.