Borrowing it
Nothing to install: this file belongs to AbdullahMalik17/Voice-Assistant17. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AbdullahMalik17/Voice-Assistant17/main/.claude/commands/sp.adr.mdgit clone --depth 1 https://github.com/AbdullahMalik17/Voice-Assistant17Wrote 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/abdullahmalik17/voice-assistant17/sp.adr)<a href="https://agentmods.dev/commands/abdullahmalik17/voice-assistant17/sp.adr"><img src="https://agentmods.dev/badge/commands/abdullahmalik17/voice-assistant17/sp.adr.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 5.1 | $0.00014 | $0.01780 |
| Opus 5 | $0.00007 | $0.00890 |
| Sonnet 5 | $0.00003 | $0.00356 |
| Haiku 4.5 | $0.00001 | $0.00178 |
Grade A, and why
sp.adr 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 6d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- sp.adr — 100% identical, 414 lines differ
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
COMMAND: Analyze planning artifacts and document architecturally significant decisions as ADRs
CONTEXT
The user has completed feature planning and needs to:
- Identify architecturally significant technical decisions from plan.md
- Document these decisions as Architecture Decision Records (ADRs)
- Ensure team alignment on technical approach before implementation
- Create a permanent, reviewable record of why decisions were made
Architecture Decision Records capture decisions that:
- Impact how engineers write or structure software
- Have notable tradeoffs or alternatives
- Will likely be questioned or revisited later
User's additional input:
$ARGUMENTS
YOUR ROLE
Act as a senior software architect with expertise in:
- Technical decision analysis and evaluation
- System design patterns and tradeoffs
- Enterprise architecture documentation
- Risk assessment and consequence analysis
OUTPUT STRUCTURE (with quick flywheel hooks)
Execute this workflow in 6 sequential steps. At Steps 2 and 4, apply lightweight Analyze→Measure checks:
- Analyze: Identify likely failure modes, specifically:
- Over-granular ADRs: ADRs that document decisions which are trivial, low-impact, or do not affect architectural direction (e.g., naming conventions, minor refactorings).
- Missing alternatives: ADRs that do not list at least one alternative approach considered.
- Measure: Apply the following checklist grader (PASS only if all are met):
- The ADR documents a decision that clusters related changes or impacts multiple components (not a trivial/single-file change).
- The ADR explicitly lists at least one alternative approach, with rationale.
- The ADR includes clear pros and cons for the chosen approach and alternatives.
- The ADR is concise but sufficiently detailed for future reference.
Step 1: Load Planning Context
Run .specify/scripts/powershell/check-prerequisites.ps1 -Json from repo root and parse JSON for FEATURE_DIR and AVAILABLE_DOCS.
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.
- 6d ago First seen · 208 lines · 14 tokens per session scan A f77a8f218498
sp.adr is a command published in the GitHub repository AbdullahMalik17/Voice-Assistant17 (11 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 1,780 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.