context-verify

A validator that checks the quality of AI coding instruction files and gives them a health score from 0 to 100.

In plain words
What is it for?
Use it to review context files, check modern Cursor and Cline formats, and catch problems before they mislead an AI coding assistant.
Why use it?
It identifies excessive length, duplicated content, stale paths, outdated files, and inconsistencies between shared and tool-specific instructions.

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/littlebearapps/contextdocs/context-verify
Any agent
npx skills add littlebearapps/contextdocs --skill context-verify
Clone the repo
git clone --depth 1 https://github.com/littlebearapps/contextdocs

Made for: Claude Code, Codex.

Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,946 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 $0.00093 $0.01946
Opus 5 $0.00046 $0.00973
Sonnet 5 $0.00019 $0.00389
Haiku 4.5 $0.00009 $0.00195

Measured yesterday against content hash 82c559399e16, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-verify 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 yesterday.

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.

.claude/skills/context-verify/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Verifier

Philosophy

Generating context files is solved — ai-context handles that. Preventing decay is not. This skill validates that AI context files remain accurate, lean, and consistent. Overstuffed context files reduce AI task success by ~3% (ETH Zurich, 2026).

Verification Checks

1. Line Budget Compliance

Check line counts and estimate tokens (lines × 4). Apply budgets:

File Warning Over Budget
AGENTS.md >120 lines >160 lines
CLAUDE.md bridge >20 lines >80 lines
Other bridge files >20 lines >60 lines

Warn on bridge length only when the extra lines appear to restate shared AGENTS.md content rather than genuine tool-specific instructions.

2. Discoverable Content Detection

Flag file tree characters (├──, └──, │), "Project Structure" sections with directory listings, dependency lists mirroring manifests, and architecture descriptions visible from source code. Report specific line numbers.

3. Stale Path Detection

Extract backtick-quoted paths from context files and verify each exists on disk. Report stale paths.

4. AGENTS-to-Bridge Consistency

Treat AGENTS.md as the canonical shared context. Bridge files may subset or reference it, but they must not contradict key commands, hard rules, naming conventions, or security notes. Flag missing bridge references (for example @AGENTS.md in CLAUDE.md) and bridges that duplicate AGENTS sections instead of staying thin.

5. MEMORY.md Drift

If a project MEMORY.md exists, check for convention-like patterns ("Always", "Never", "Use") not yet promoted to CLAUDE.md.

6. Context Guard Status (Claude Code, Gemini CLI, Copilot, Cursor)

Check for hook scripts and registration entries. In Claude Code: .claude/hooks/context-*.sh and .claude/settings.json. Other platforms use their own hook directories.

7. Context Load (Aggregate Token Estimate)

Calculate per-tool aggregate token load using the tool-to-file mapping from .claude/rules/context-quality.md. Thresholds: <5,000 tokens healthy, 5,000–10,000 warning, >10,000 over budget.

Read the full file on GitHub · 152 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. yesterday First seen · 152 lines · 93 tokens per session scan A 82c559399e16

Subscribe to this mod's changes

context-verify is a skill published in the GitHub repository littlebearapps/contextdocs (5 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 1,946 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

skill-creator-primer

You MUST load this skill before the skill-creator skill AND before making ANY change to, or conducting a review of ANY Agent Skill. Triggers include creating, editing, reviewing, or contributing to any part of an Agent Skill (description, frontmatter, body, references, scripts, trigger evals, conflicts, etc).

sammcj/agentic-coding · 74 tokens

llm-wiki

Use when building or maintaining a self-contained personal knowledge base (an LLM wiki) in plain markdown. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki health, auditing article claims against their sources, critiquing a wiki source's reasoning, superseding stale knowledge, 'add to…

sammcj/agentic-coding · 82 tokens

apply-mantel-styles

Provides guidelines for applying Mantel's brand styles to diagrams and frontend components. Use when asked to create visuals that need to align with Mantel's branding.

sammcj/agentic-coding · 37 tokens

extract-wisdom

Extract wisdom, insights, and actionable takeaways from YouTube videos, blog posts, articles, or text files. Use when asked to extract wisdom or key insights from a given content source.

sammcj/agentic-coding · 43 tokens

home-assistant

This skill should be used when helping with Home Assistant setup, including creating automations, modifying dashboards, checking entity states, debugging automations, and managing the smart home configuration. Use this for queries about HA entities, YAML automation/dashboard generation, or troubleshooting HA issues.

sammcj/agentic-coding · 57 tokens

aws-strands-agents-agentcore

Use when working with AWS Strands Agents SDK or Amazon Bedrock AgentCore platform for building AI agents. Provides architecture guidance, implementation patterns, deployment strategies, observability, quality evaluations, multi-agent orchestration, and MCP server integration.

sammcj/agentic-coding · 55 tokens