requirements

requirements is a skill for Claude Code, Codex from ptsilivis/autonomousguy. It costs 221 tokens per session (3,727 once invoked), scanned A, original, MIT.

A requirements-engineering guide that turns informal descriptions into clear, testable requirements and links them to design and tests. EARS is a structured way to write requirements with predictable conditions and expected behavior.

In plain words
What is it for?
Use it to extract or refine requirements, record open questions and safety attributes, and build traceability from system requirements through software design to tests.
Why use it?
It removes ambiguity from briefs and specifications and makes it easier to verify that the implemented system matches what was requested.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/ptsilivis/autonomousguy/requirements
Any agent
npx skills add ptsilivis/autonomousguy --skill requirements
Clone the repo
git clone --depth 1 https://github.com/ptsilivis/autonomousguy

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for requirements

README.md
[![agentmods](https://agentmods.dev/badge/skills/ptsilivis/autonomousguy/requirements.svg)](https://agentmods.dev/skills/ptsilivis/autonomousguy/requirements)
Your own site
<a href="https://agentmods.dev/skills/ptsilivis/autonomousguy/requirements"><img src="https://agentmods.dev/badge/skills/ptsilivis/autonomousguy/requirements.svg" alt="Measured on agentmods" height="20"></a>
Per session 221 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,727 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00221 $0.03727
Opus 5 $0.00111 $0.01863
Sonnet 5 $0.00044 $0.00745
Haiku 4.5 $0.00022 $0.00373

Measured 5d ago against content hash 3718627111b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

requirements 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 5d 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.

skills/requirements/requirements/SKILL.md · 299 lines

How it starts

The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Requirements Engineering

Context

You are a requirements engineer with expertise in embedded automotive systems and functional safety (ISO 26262-6, ASPICE SWE.1 / SWE.6). You elicit structured, testable requirements from informal stakeholder inputs, refine coarse system-level requirements into precise software requirements, and build bidirectional traceability across SYS-REQ → SW-REQ → design → test. You apply EARS notation, SMART criteria, and automotive-specific attributes (safety-relevance, ASIL, traceability to system requirements).

Instructions

Decide mode from the input:

  • Informal brief, meeting notes, customer text, or system spec → Elicitation.
  • One or more existing requirements that are vague, compound, or untestable → Refinement.
  • A list of requirements + design artefacts + tests → Traceability.
  • Combination → run modes in order (Elicitation → Refinement of any vague output → Traceability against design/test sets if provided).

Operating principles (apply to every response)

Work autonomously within a single pass - no follow-up prompt should be needed:

  1. Self-directed scope. Extract every requirement implied by the input, not only the one asked about. If the brief implies adjacent safety or interface requirements, surface them and note the broadened scope.
  2. Decision-ready output. Each requirement is delivered complete: EARS statement plus the full attribute set (ID, type, priority, ASIL, verification method, source) - so it is review-ready without a follow-up.
  3. Self-check before returning. Verify each requirement against its hard rules: atomic (one behaviour), testable (a verification method fits), in a valid EARS pattern, with no implementation prescription, and ASIL-tagged items carry a verification method. State the result on its own line: Verified against: <checks run>; could not verify: <stakeholder intent, traces to artifacts not provided>.
  4. Confidence and gaps. Mark inferred attributes (especially ASIL) as inferred, list open questions where intent is ambiguous, and call out where a stakeholder must decide before the requirement is baselined.

Read the full file on GitHub · 299 lines

Changes

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.

  1. 5d ago First seen · 299 lines · 221 tokens per session scan A 3718627111b8

Subscribe to this mod's changes

requirements is a skill published in the GitHub repository ptsilivis/autonomousguy (29 stars, last pushed 2mo ago), licensed MIT. It adds 221 tokens to every session and 3,727 once invoked, about $0.0011 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.