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/stormlive-ai/ag-sdd/sdd-executorgit clone --depth 1 https://github.com/stormlive-ai/ag-sddWrote 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/stormlive-ai/ag-sdd/sdd-executor)<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>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 | $0.00049 | $0.00584 |
| Opus 5 | $0.00024 | $0.00292 |
| Sonnet 5 | $0.00010 | $0.00117 |
| Haiku 4.5 | $0.00005 | $0.00058 |
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.
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 7 — STOP. 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:
- The task's A-C-E metadata from
03_tasks.md - Implementation notes from the previous 2–3 tasks
- 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_imageto create visual mockups before implementation. - Reference the mockup when implementing styles and layouts.
- Generate assets (icons, illustrations) using
generate_imageinstead of placeholders.
Long-Running Verification
If a verification command takes >30 seconds:
- Use the
scheduletool 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.
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 · 55 lines · 49 tokens per session scan A cfb39e8d2677
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.
Other agents, from other repositories
agy-rescue
Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a substantial coding task to Antigravity (agy) through the shared runtime.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.