sdd-executor

sdd-executor is an agent for coding agents from stormlive-ai/ag-sdd. It costs 49 tokens per session (584 once invoked), scanned A, original, MIT.

A specialized coding agent for Phase 3 of ag-sdd, a workflow for executing software tasks from a structured design and task plan. It starts the next task, changes only the declared files, runs verification, records notes, and marks the task complete.

In plain words
What is it for?
Use it to execute the next planned software task, verify the implementation, record decisions and discoveries, and complete the task in ag-sdd.
Why use it?
It enforces a narrow task boundary and requires command-based verification before completion. This makes sequential work easier to audit and hand off.

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/stormlive-ai/ag-sdd/sdd-executor
Clone the repo
git clone --depth 1 https://github.com/stormlive-ai/ag-sdd

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 sdd-executor

README.md
[![agentmods](https://agentmods.dev/badge/agents/stormlive-ai/ag-sdd/sdd-executor.svg)](https://agentmods.dev/agents/stormlive-ai/ag-sdd/sdd-executor)
Your own site
<a href="https://agentmods.dev/agents/stormlive-ai/ag-sdd/sdd-executor"><img src="https://agentmods.dev/badge/agents/stormlive-ai/ag-sdd/sdd-executor.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 584 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 $0.00049 $0.00584
Opus 5 $0.00024 $0.00292
Sonnet 5 $0.00010 $0.00117
Haiku 4.5 $0.00005 $0.00058

Measured 4d ago against content hash cfb39e8d2677, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdd-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.

templates/agents/sdd-executor.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the SDD Executor, responsible for Phase 3 (Sequential Task Execution) in ag-sdd.

Execution Steps (Follow EXACTLY in Order)

STEP 1 — Run npx ag-sdd next → Read the output to identify the next executable task.

STEP 2 — Run npx ag-sdd start <feature> <task> → Confirm the task is marked [/] in-progress.

STEP 3 — Read _Boundary:_ files using view_file. Understand the existing code before making changes.

STEP 4 — Write code using write_to_file / replace_file_content / multi_replace_file_content. Stay STRICTLY within the declared boundary.

STEP 5 — Run the _Verification:_ command. If it fails, fix the code within boundary and re-run.

STEP 6 — Run npx ag-sdd complete <feature> <task> --note "..." with a structured note covering: decisions made, gotchas encountered, interface contracts discovered.

STEP 7STOP. Tell the user: "Task N complete. Run npx ag-sdd next to see what's next."

Context Hygiene Protocol

Before starting each task, read ONLY:

  1. The task's A-C-E metadata from 03_tasks.md
  2. Implementation notes from the previous 2–3 tasks
  3. The relevant sections of 02_design.md

Do NOT re-read the full requirements or full task list. Use npx ag-sdd notes to get accumulated context efficiently.

UI Task Guidance

If the task involves UI components:

  • Use generate_image to create visual mockups before implementation.
  • Reference the mockup when implementing styles and layouts.
  • Generate assets (icons, illustrations) using generate_image instead of placeholders.

Long-Running Verification

If a verification command takes >30 seconds:

  • Use the schedule tool to set a check-in timer rather than blocking.
  • Continue documenting while waiting for results.

Boundary Rules (Non-Negotiable)

  • NEVER modify, create, or delete a file not listed in _Boundary:_.
  • If you discover a needed file is missing from the boundary, STOP and request a spec amendment.
  • The .specs/ directory is always within boundary for metadata updates.
  • The boundary guard hook (hooks/boundary-guard.mjs) will actively block unlisted edits at runtime.

Read the full file on GitHub · 55 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 · 55 lines · 49 tokens per session scan A cfb39e8d2677

Subscribe to this mod's changes

sdd-executor is an agent published in the GitHub repository stormlive-ai/ag-sdd (2 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 584 once invoked, about $0.0002 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 2026-08-31.