agentmods.dev

claude-context: Skill for Claude Code

.agents/skills/spec-requirements/SKILL.md

spec-requirements is a skill for Claude Code from lbruton/claude-context. It costs 36 tokens per session (965 once invoked), scanned A, original, MIT.

A specification step that questions an issue and writes its requirements in EARS form. EARS is a structured way to state software behaviour using conditions such as when, if, and while.

In plain words
What is it for?
Use it to inspect an issue, ask clarifying questions, and create the requirements document for a planned change.
Why use it?
It turns an incomplete or ambiguous issue into clearer requirements before design and implementation start.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is lbruton/claude-context's own configuration. It tells Claude Code how to work on claude-context itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-context configures →

not rated 2repo +1 changed 5d ago A scan 36 tokens original MIT
View source ↗ lbruton/claude-context
Reuse

Borrowing it

Nothing to install: this file belongs to lbruton/claude-context. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lbruton/claude-context/master/.agents/skills/spec-requirements/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lbruton/claude-context

Made for: Claude Code.

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 spec-requirements

README.md
[![agentmods](https://agentmods.dev/badge/skills/lbruton/claude-context/spec-requirements/github.svg)](https://agentmods.dev/skills/lbruton/claude-context/spec-requirements)
Your own site
<a href="https://agentmods.dev/skills/lbruton/claude-context/spec-requirements"><img src="https://agentmods.dev/badge/skills/lbruton/claude-context/spec-requirements/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.

agentmods 80×15 button for spec-requirements

Your own site · 80×15
<a href="https://agentmods.dev/skills/lbruton/claude-context/spec-requirements"><img src="https://agentmods.dev/badge/skills/lbruton/claude-context/spec-requirements.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 965 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00036 $0.00965
Opus 5.5 $0.00014 $0.00386
Sonnet 5.5 $0.00007 $0.00193
Haiku 4.5 $0.00004 $0.00097

Measured 5d ago against content hash 5e52db28d55b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

spec-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.

.agents/skills/spec-requirements/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/spec-requirements ISSUE

Phase 1 of the spec lifecycle: interrogate the issue with /grill, then write requirements.md in EARS syntax. One artifact, then STOP.

Invocation

/spec-requirements <ISSUE-ID>

If <ISSUE-ID> is missing, print Usage: /spec-requirements <ISSUE-ID> and exit. Do not guess.

Read first — shared conventions

Read .agents/skills/spec/references/conventions.md (universal mechanics: folder resolution, phase-boundary discipline, unreconciled-marks pre-check, the approved: rule) and the active project's .context/spec-conventions.md if present. Single source of truth; this skill does not restate them.

Steps

  1. Resolve the spec folder per conventions.md. If none exists, STOP: "no spec found for {ISSUE-ID} — run /spec new {ISSUE-ID} \"<slug>\" first." Confirm requirements.md is the (scaffolded, near-empty) target; if it already has substantial body, surface that and ask before overwriting.

  2. Grill the issue — proportional to how well-specified it already is.

    • Inspect the issue body / "Source Issue" block for an existing ## Discovery brief (from /discover).
    • No discovery brief, or thin issue → invoke the /grill {ISSUE-ID} skill and conduct the full interrogation. Do NOT reimplement interrogation inline — grill owns that domain (it reads .context/GLOSSARY.md, challenges terminology, cross-references the live codebase, walks decision dependencies, and emits a Grill Brief).
    • Discovery brief already present → grill is largely done; run a light pass only on items the brief left open. Don't re-interrogate resolved questions.
    • Carry grill's Grill Brief (Decisions / Terms / Open Questions) forward as the raw material for the requirements.

  3. Draft requirements.md from the brief, per the template:

    • User stories (context — the who/why): As a … I want … so that …
    • Acceptance criteria in EARS (the testable normative statements — replaces loose Given/When/Then). Pick the right pattern per requirement:
      Pattern Template
      Ubiquitous The <system> SHALL <response>
      Event-driven WHEN <trigger>, the <system> SHALL <response>
      State-driven WHILE <state>, the <system> SHALL <response>
      Unwanted IF <condition>, THEN the <system> SHALL <response>
      Optional WHERE <feature>, the <system> SHALL <response>
      Each EARS line must be individually testable — it becomes a TDD Cohort B assertion downstream.
    • Explicit non-goals.
    • Keep scope tight — specs carry no NFR matrix, stakeholder analysis, or risk register. If the work needs that depth, surface it and stop.

Read the full file on GitHub · 67 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 Changed 5e52db28d55b
  2. 9d ago Changed 2687543b05a0
  3. 11d ago First seen · 67 lines · 36 tokens per session scan A 8792cbdb1d48

Subscribe to this mod's changes

spec-requirements is a skill published in the GitHub repository lbruton/claude-context (2 stars, last pushed 5d ago), licensed MIT. It adds 36 tokens to every session and 965 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-17.

PlanningWriting and docs
Related

Other skills, from other repositories

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens