claude-context: Skill for Claude Code

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

spec-approach is a skill for Claude Code from lbruton/claude-context. It costs 38 tokens per session (559 once invoked), scanned A, original, MIT.

A specification-planning step that turns requirements and research into an implementation approach. It records the architecture, important technical choices, and the files or modules that will change.

In plain words
What is it for?
Use it after requirements and discovery are complete to define how a feature will be built, document trade-offs, map file changes, and describe the interface contract when mockups or prototypes are involved.
Why use it?
It gives implementation a checked plan instead of leaving design decisions implicit. It also catches unresolved review comments before the approach is written.

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 →

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-approach/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-approach

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/lbruton/claude-context/spec-approach"><img src="https://agentmods.dev/badge/skills/lbruton/claude-context/spec-approach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 559 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 $0.00038 $0.00559
Opus 5.5 $0.00015 $0.00224
Sonnet 5.5 $0.00008 $0.00112
Haiku 4.5 $0.00004 $0.00056

Measured 5d ago against content hash 34300439f444, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

spec-approach 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-approach/SKILL.md · 51 lines

What it actually says

/spec-approach ISSUE

Phase 3: decide how we'll build it, into approach.md. One artifact, then STOP.

Invocation

/spec-approach <ISSUE-ID>

Missing <ISSUE-ID> → print Usage: /spec-approach <ISSUE-ID> and exit.

Read first — shared conventions

Read .agents/skills/spec/references/conventions.md and the project's .context/spec-conventions.md if present.

Steps

  1. Resolve the spec folder; read requirements.md + discovery.md (both inputs).
  2. Unreconciled-marks PRE-CHECK (per conventions.md) on both prior files. If any unreconciled marks exist, STOP: "{file} has not been reconciled — run /spec-reconcile {ISSUE-ID} {phase} first."
  3. Draft approach.md per the template:
    • High-level architecture (1–3 paragraphs).
    • Key technical decisions — each with a one-line rationale + the tradeoff it accepts (a decision with no loser is not a real decision).
    • File/module map — files to be Created / Modified / Deleted. This map is the contract the tasks phase cross-checks against.
    • UI Contract (MANDATORY if requirements.md or discovery.md references any mockup, playground file, screenshot, or prototype): mockup artifact paths, named states/screens, component/token requirements, interaction contract. If purely backend/data/config, write N/A — no UI surface.
    • Out-of-scope items pushed to follow-up issues.
  4. Save approach.md. Touch no other file.

Output

One-paragraph summary, then:

next: /spec-review {ISSUE-ID} approach [AGENT]
then: /spec-reconcile {ISSUE-ID} approach
then: /spec-tasks {ISSUE-ID}

Do NOT

  • Write code, draft tests, or decide implementation order — that's the tasks phase.
  • Add files the discovery findings don't justify, or contradict requirements.md silently (surface conflicts and stop).
  • Touch any file other than approach.md. Advance phases. Stamp approved:.
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 34300439f444
  2. 9d ago Changed 54af1c605559
  3. 11d ago First seen · 51 lines · 38 tokens per session scan A c170f5dc5ce9

Subscribe to this mod's changes

spec-approach is a skill published in the GitHub repository lbruton/claude-context (2 stars, last pushed 5d ago), licensed MIT. It adds 38 tokens to every session and 559 once invoked, about $0.0002 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.

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