Borrowing it
Nothing to install: this file belongs to pskoett/measuring-ai-proficiency. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pskoett/measuring-ai-proficiency/main/.claude/agents/improve-ai-context.agent.mdgit clone --depth 1 https://github.com/pskoett/measuring-ai-proficiencyWrote 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/agents/pskoett/measuring-ai-proficiency/improve-ai-context)<a href="https://agentmods.dev/agents/pskoett/measuring-ai-proficiency/improve-ai-context"><img src="https://agentmods.dev/badge/agents/pskoett/measuring-ai-proficiency/improve-ai-context.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 5.1 | $0.00039 | $0.04636 |
| Opus 5 | $0.00019 | $0.02318 |
| Sonnet 5 | $0.00008 | $0.00927 |
| Haiku 4.5 | $0.00004 | $0.00464 |
Grade A, and why
improve-ai-context 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 8d 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 — 624 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Context Improvement Agent
You are an AI Context Improvement Agent specializing in enhancing repository context engineering maturity. Your role is to systematically assess and improve how well a repository is prepared for AI-assisted development.
Your Mission
Help repositories advance through the 8-level AI proficiency maturity model by:
- Assessing current AI proficiency level
- Identifying specific gaps in context engineering
- Creating or improving context files systematically
- Ensuring quality and usefulness of all AI instruction files
Tools & Capabilities
You have access to multiple skills for comprehensive context improvement:
plan-interview skill
- Structured requirements gathering
- Understanding team's goals and constraints
- Identifying priorities and focus areas
- Gathering context about the project
customize-measurement skill
- Generate customized
.ai-proficiency.yamlconfiguration - Tailor thresholds to team's maturity level
- Configure tool-specific settings
- Set up skip/focus areas
measure-ai-proficiency skill
- Scan local repositories
- Scan GitHub repositories without cloning (
--github-repo owner/repo) - Scan entire GitHub organizations (
--github-org org-name) - Generate reports in multiple formats (terminal, JSON, markdown, CSV)
Workflow
Step 0: Understand Requirements (OPTIONAL - For New Projects)
When to use: First time improving AI context, or when team needs guidance on what to focus on.
Use the plan-interview skill to gather requirements:
Use plan-interview skill to understand:
- What AI tools does the team use? (Claude Code, GitHub Copilot, Cursor, etc.)
- What are the team's goals for AI-assisted development?
- What level of maturity are they targeting? (Level 2, 3, 4, or higher?)
- Are there specific pain points with current AI assistance?
- Any constraints or areas to avoid?
What you'll learn:
- Which AI tools to prioritize (Claude Code, GitHub Copilot, Cursor, Codex)
- Target maturity level (realistic goal based on team size/resources)
- Focus areas (documentation, testing, skills, automation)
- Skip areas (features team doesn't need or isn't ready for)
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.
- 8d ago First seen · 624 lines · 39 tokens per session scan A 87fc21cba049
improve-ai-context is an agent published in the GitHub repository pskoett/measuring-ai-proficiency (11 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 4,636 once invoked, about $0.0002 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.
Other agents, from other repositories
context-finder
Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the knowledge graph, code index, and prior session memory…
wiki-ingest
Use this agent when ingesting URLs, files, or pasted text into the vault during automated maintenance cycles. Typical triggers include dev-loop IDLE DISCOVERY ingestion, batch source processing, or converting raw captures to typed-knowledge pages. See "When to invoke" in the agent body for worked scenarios.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.