Borrowing it
Nothing to install: this file belongs to jnarowski/agentcmd. 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/jnarowski/agentcmd/main/.claude/commands/cmd/generate-feature-spec.mdgit clone --depth 1 https://github.com/jnarowski/agentcmdWrote 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/jnarowski/agentcmd/generate-feature-spec)<a href="https://agentmods.dev/commands/jnarowski/agentcmd/generate-feature-spec"><img src="https://agentmods.dev/badge/commands/jnarowski/agentcmd/generate-feature-spec/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/jnarowski/agentcmd/generate-feature-spec"><img src="https://agentmods.dev/badge/commands/jnarowski/agentcmd/generate-feature-spec.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 | $0.00008 | $0.03680 |
| Opus 5.5 | $0.00003 | $0.01472 |
| Sonnet 5.5 | $0.00002 | $0.00736 |
| Haiku 4.5 | $0.00001 | $0.00368 |
Grade C, and why
generate-feature-spec scanned grade C with 1 finding 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 2mo 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- prettier-ignore-start --> How it starts
The opening of the file, as written. The whole thing — 469 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Specification
Generate a comprehensive spec document for new features with phases, complexity estimates, and test plans. Generates a well-structured implementation spec and saves it to .agent/specs/todo/[id]-[feature]/spec.md with timestamp-based ID.
Variables
- $param1: $1 (optional) - Feature context or description (infers from conversation if omitted)
Instructions
- IMPORTANT: Use your reasoning model - THINK HARD about feature requirements, design, implementation approach, AND complexity
- IMPORTANT: This command ONLY generates the spec - do NOT implement any code or make file changes beyond creating the spec folder/file and updating index.json
- Your ONLY file operations: create spec folder, write spec.md, update index.json - nothing else
- Normalize feature name to kebab-case for the folder name
- Replace ALL
<placeholders>with specific details relevant to that section - Create detailed step-by-step tasks grouped logically (e.g., by phase, component, or feature area)
- Assign complexity score (1-10) to EVERY task based on context needs (see Complexity Scale below)
- Order tasks by dependencies (foundation → core → integration)
- Include specific file paths, not generic names
- Make all commands copy-pasteable with expected outputs
- Include comprehensive verification covering build, tests, linting, and manual checks
- Add E2E test tasks if feature has UI
- Keep acceptance criteria measurable
- DO NOT include hour-based estimates anywhere - use complexity points only
Task ID Format
Use phase.task notation for all tasks:
- Format:
1.1,1.2,2.1,2.2, etc. - Phase number matches the Phase heading number
- Task numbers increment sequentially within each phase
- Example: Phase 1 tasks →
1.1,1.2,1.3; Phase 2 tasks →2.1,2.2
Folder Structure
Specs are organized by lifecycle stage:
todo/- New specs ready to implement (Status:draftorin-progress)backlog/- Lower priority specs not yet starteddone/- Completed and reviewed specs (Status:completed)
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.
- 2mo ago First seen · 469 lines · 8 tokens per session scan C e3544dc667b7
generate-feature-spec is a command published in the GitHub repository jnarowski/agentcmd (18 stars, last pushed 10mo ago), licensed MIT. It adds 8 tokens to every session and 3,680 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
generate-feature-spec compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| generate-feature-specjnarowski/agentcmd | Command | 18 | 10mo ago | MIT | C | 8 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | yesterday | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 148k | yesterday | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | yesterday | MIT | A | 14 | Claude Code |