validate

A user-run review check for a project's structured YAML context and generated files. It checks required fields, linked documents, consistency, content gaps, and compilation output.

In plain words
What is it for?
Use it to review structured project context, confirm that referenced documents and imports resolve, and identify items that need human attention.
Why use it?
It helps find broken references, missing information, placeholders, and out-of-sync generated files before the project is versioned.

Skill for Claude CodeCodex

Part of the scs-team plugin — 7 skills shipped together

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/tim-mccrimmon/structured-context-spec/validate
Any agent
npx skills add tim-mccrimmon/structured-context-spec --skill validate
Clone the repo
git clone --depth 1 https://github.com/tim-mccrimmon/structured-context-spec

Made for: Claude Code, Codex.

Or install scs-team, the plugin that ships this one along with the rest of its 7 skills.

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,898 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 $0.00024 $0.01898
Opus 5 $0.00012 $0.00949
Sonnet 5 $0.00005 $0.00380
Haiku 4.5 $0.00002 $0.00190

Measured 3d ago against content hash 7cd741946429, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validate 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 3d 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.

plugins/scs-team/skills/validate/SKILL.md · 240 lines

How it starts

The opening of the file, as written. The whole thing — 240 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-team:validate. Never auto-invoke based on project state or conversation context.

SCS Team Validate - Structure Check and Review Surface

You are validating the user's structured context and surfacing issues that need human review before versioning.

Validation Levels

Level 1: Syntax

  • Valid YAML
  • Required fields present (id, version, title, description)
  • Correct structure

Level 2: References

  • All SCDs referenced in bundles exist
  • All bundle imports can be resolved
  • No circular dependencies

Level 3: Consistency

  • Version consistency (all DRAFT or all versioned)
  • Tier consistency (SCDs in correct tier)
  • ID format correctness

Level 4: Content Quality (Human Review Items)

  • Placeholder content detection
  • Incomplete sections
  • Generic/template text not customized
  • TBD items that need resolution

Level 5: Compilation Check

  • Compiled output exists in .claude/rules/ for each concern with SCDs
  • Compiled files have <!-- scs-team:managed --> ownership header
  • CLAUDE.md has <!-- scs-team:start --> / <!-- scs-team:end --> markers
  • Compiled output is not stale (all concerns with SCDs have corresponding rules files)

Concern Coverage Assessment

Assess coverage across all 11 concerns:

# Concern Expected SCDs
1 Architecture system-context, tech-stack, integration-map, component-model
2 Security authn-authz, data-protection, data-handling, threat-model
3 Performance & Reliability response-time, availability, fault-tolerance, scalability
4 Usability & Accessibility ux-principles, accessibility-compliance, error-handling-ux
5 Compliance & Governance hipaa-compliance, soc2-controls, audit-requirements, policy-enforcement
6 Data & Provenance data-model, provenance-tracking, retention-policy
7 Testing & Validation test-coverage, validation-plan, qa-procedures
8 Deployment & Operations infrastructure-definition, observability, incident-response
9 Safety & Risk risk-assessment, safety-checklist
10 Ethics & AI Accountability ai-usage-policy, audit-trail, model-bias
11 Business Context problem-definition, stakeholders, business-objectives, opportunity-analysis, constraints-and-assumptions, success-criteria

Read the full file on GitHub · 240 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. 3d ago First seen · 240 lines · 24 tokens per session scan A 7cd741946429

Subscribe to this mod's changes

validate 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 24 tokens to every session and 1,898 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.