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 skills/tim-mccrimmon/structured-context-spec/explainnpx skills add tim-mccrimmon/structured-context-spec --skill explaingit clone --depth 1 https://github.com/tim-mccrimmon/structured-context-specWrote 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/skills/tim-mccrimmon/structured-context-spec/explain)<a href="https://agentmods.dev/skills/tim-mccrimmon/structured-context-spec/explain"><img src="https://agentmods.dev/badge/skills/tim-mccrimmon/structured-context-spec/explain.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 | $0.00018 | $0.00978 |
| Opus 5 | $0.00009 | $0.00489 |
| Sonnet 5 | $0.00004 | $0.00196 |
| Haiku 4.5 | $0.00002 | $0.00098 |
Grade A, and why
explain 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 4d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Invocation Rules
- User-initiated only: Do NOT invoke this skill unless the user explicitly runs
/scs-vibe:explain. Never auto-invoke based on project state or conversation context.
Why Structured Context Matters (For Vibe Coders)
You're explaining the value of structured context to a developer who may be skeptical or just curious.
The Core Message
Keep it practical and relatable. Don't oversell. The message is:
"Claude is smart but doesn't know YOUR system. Without explicit context, it makes confident decisions based on general knowledge - which often codes you into corners. Structured context gives Claude a 'world' to operate in."
Key Points to Cover
1. The Problem (Make It Relatable)
Share scenarios they've probably experienced:
- "Claude suggested a perfectly reasonable solution... that conflicted with a design decision you made 3 months ago"
- "Claude built a feature that works in isolation but doesn't fit your existing patterns"
- "Every new session, you're re-explaining your architecture"
- "Claude invented an abstraction you now have to maintain, when a simpler approach would have worked"
The root cause: Claude has vast general knowledge but zero knowledge of YOUR specific system. It fills the gaps with reasonable-sounding guesses.
2. The Solution (Keep It Simple)
Structured context = telling Claude about your system BEFORE it starts making decisions.
It's like onboarding a new developer:
- Here's what we're building
- Here's how it's structured
- Here are the patterns we use (and avoid)
- Here are the constraints you need to know
The key insight: This isn't about making Claude smarter. It's about giving it the information it needs to apply its intelligence appropriately.
3. What Goes in Structured Context
The essentials:
- System Overview: What does this do? Who uses it?
- Architecture: How is it structured? What are the key components?
- Tech Stack: What specific technologies and why?
- Patterns: What patterns do we use? What do we avoid?
- Constraints: What limits must Claude respect?
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.
- 4d ago First seen · 119 lines · 18 tokens per session scan A ed282d098c13
explain is a skill published in the GitHub repository tim-mccrimmon/structured-context-spec (19 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 978 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 2026-08-30.
Other skills, from other repositories
good-skill
Use only for fixture validation of narrow skill routing. Avoid for normal repo work.
broad-skill
Always use this skill for every task and all tasks.
caveman-fixture
Always use caveman terse speech for every task.
acontext-installer
Install Acontext, Login & Init Acontext Project, Add Skill Memory to Agent.
missing-description
No description.
semantic-search
Zero-dependency TF-IDF search across MUSE memory, roles, and skills. Use when user wants to find information across their project context.