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 commands/emaraschio/cursor-commands/requirement-to-implementationgit clone --depth 1 https://github.com/emaraschio/cursor-commandsWrote 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/emaraschio/cursor-commands/requirement-to-implementation)<a href="https://agentmods.dev/commands/emaraschio/cursor-commands/requirement-to-implementation"><img src="https://agentmods.dev/badge/commands/emaraschio/cursor-commands/requirement-to-implementation.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 | $0.00020 | $0.00528 |
| Opus 5 | $0.00010 | $0.00264 |
| Sonnet 5 | $0.00004 | $0.00106 |
| Haiku 4.5 | $0.00002 | $0.00053 |
Grade A, and why
requirement-to-implementation 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.
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Take a requirement (feature, bug, refactor, chore, or performance task) from any source through intake, exploration, an approved plan, implementation, and documentation. Full workflow: .cursor/skill-contracts/requirement-to-implementation/SKILL.md (user install: ~/.cursor/skill-contracts/requirement-to-implementation/SKILL.md).
Defaults
None. See skill for workflow defaults.
Steps
- Read
.cursor/skill-contracts/requirement-to-implementation/SKILL.mdfor the full agent contract; if that file is missing, read~/.cursor/skill-contracts/requirement-to-implementation/SKILL.md. - Execute phases in order (Intake → Context → Explore → Plan → [Approve] → Implement → Document); do not skip the approval gate.
- Report outcomes per skill (requirement summary, plan, verification, memory-bank updates as specified).
Anti-patterns
- Do not implement before plan approval. Trigger: the user asks to implement immediately. Wrong: writing production code before presenting a plan and getting approval. Correct: present the structured plan and wait for explicit approval before implementing. Reason: plans are cheap and rework is expensive, and unapproved changes can go the wrong direction.
- Do not skip intake or exploration. Trigger: an ambiguous requirement. Wrong: jumping to a plan without intake questions or codebase exploration. Correct: run intake and exploration to map the blast radius before planning. Reason: skipping discovery produces plans that miss affected files and risks.
- Commit only when asked. Trigger: finishing implementation. Wrong: committing or pushing without an explicit request. Correct: stop after verifying and let the user request the commit. Reason: surprise commits and pushes are hard to undo.
Examples
/requirement-to-implementation/requirement-to-implementationwith a GitHub issue URL or pasted ticket
Maintainers
Behavioral eval: .cursor/skill-contracts/requirement-to-implementation/eval/cases.md. Ship gate sections: A, S before changing SKILL.md or this command.
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 · 40 lines · 20 tokens per session scan A 0be77f38c47f
requirement-to-implementation is a command published in the GitHub repository emaraschio/cursor-commands (9 stars, last pushed 29d ago), licensed MIT. It adds 20 tokens to every session and 528 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 2026-08-31.
Other commands, from other repositories
grok_init
Discover, verify, and persist the local HTTP proxy used by Grok Build Supervisor.
analyze-deps
Analyze the project's dependency tree, identify unused or duplicate dependencies, and suggest optimizations.
code-review
Review the code changes in this conversation (or the files I've @-mentioned) systematically.
security-audit
Perform a security-focused review of the code I've @-mentioned (or the most relevant changes in this conversation).
update-deps
Update the project's dependencies and ensure the project still works.
fix-issue
Command "fix-issue" from HKTITAN/cursor-best-practices, covering steps and rules.