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.
git clone --depth 1 https://github.com/attilaszasz/sdd-pilotWrote 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/commands/attilaszasz/sdd-pilot/sddp-plan)<a href="https://agentmods.dev/commands/attilaszasz/sdd-pilot/sddp-plan"><img src="https://agentmods.dev/badge/commands/attilaszasz/sdd-pilot/sddp-plan/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/attilaszasz/sdd-pilot/sddp-plan"><img src="https://agentmods.dev/badge/commands/attilaszasz/sdd-pilot/sddp-plan.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.00321 |
| Opus 5.5 | $0.00000 | $0.00128 |
| Sonnet 5.5 | $0.00000 | $0.00064 |
| Haiku 4.5 | $0.00000 | $0.00032 |
Grade A, and why
sddp-plan 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 1mo 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.
What it actually says
Command description: Create an implementation plan from the current feature specification.
Argument hint: [optional: planning constraints or focus areas]
Command category: feature-delivery
Prerequisites: spec
You are starting a planning workflow. Your sole purpose is to create an implementation plan from the specification — architecture decisions, data models, API contracts, and technology choices. Disregard any prior context from this conversation. Focus exclusively on technical planning.
$ARGUMENTS = The user's prompt text provided alongside this command invocation. If no prompt text was provided, set $ARGUMENTS to empty and let the skill handle it.
Load and follow the workflow in .github/sddp/workflows/plan-feature/WORKFLOW.md.
The selected agent dispatches each Delegate target through its declared agents allowlist:
- Delegate: Spec Validator →
.github/agents/_spec-validator.md(only during Spec → Plan gate, Step 1.6) - Delegate: Context Gatherer →
.github/agents/_context-gatherer.md - Delegate: Database Administrator →
.github/agents/_database-administrator.md - Delegate: API Designer →
.github/agents/_api-designer.md - Delegate: Policy Auditor →
.github/agents/_policy-auditor.md - Delegate: Technical Researcher →
.github/agents/_technical-researcher.md
Report progress to the user at each major milestone — summarize what has been completed and what remains.
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.
- 1mo ago Changed · -4 lines · -10 tokens per session e0b502f4d914
- 1mo ago First seen · 28 lines · 10 tokens per session scan A 361880aeedca
sddp-plan is a command published in the GitHub repository attilaszasz/sdd-pilot (98 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 321 tokens. 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 2026-09-03.
Other commands, from other repositories
release
Prepare and publish spec-driven-steroids through the tag-triggered npm release pipeline.
inject-guidelines.command
Review repository guidelines using the project-guidelines-writer skill. Create missing documents as ordinary Markdown, apply only justified incremental updates to existing files, and leave unchanged files unwritten.
spec-driven.command
Start an approved Spec-Driven workflow using the brief or full lane.
util.gh-pr-review
Generate pull request review using architecture overview context.
util.gh-pr-content
Create pull request content from the current branch changes.
util.git-commit-message
Generate conventional commit message and description from the current changes diff.