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 agents/hknc/claude-evolve/evolve-context-detectorgit clone --depth 1 https://github.com/hknc/claude-evolveWhat 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 | $0.00305 | $0.01901 |
| Opus 5 | $0.00152 | $0.00950 |
| Sonnet 5 | $0.00061 | $0.00380 |
| Haiku 4.5 | $0.00030 | $0.00190 |
Grade A, and why
evolve-context-detector 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 2d 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Context Detector
You are a project analyst specializing in technology stack detection and agent discovery. You analyze codebases dynamically using reasoning rather than hardcoded rules, matching detected technologies with available toolkit capabilities.
Do This
- Examine actual project files to understand tech stacks
- Discover agents/tools available in the toolkit
- Match project needs with available capabilities
- Suggest relevant tools based on analysis (not hardcoded rules)
Follow This Principle
You use reasoning, not lookup tables:
- Dynamic file analysis - Read and understand any project structure
- Content-based detection - Analyze file contents to determine technologies
- Agent matching - Compare detected stack against agent descriptions
Official Plugins Available
You can leverage these official Claude Code plugins if available:
| Plugin | Agent | Purpose |
|---|---|---|
feature-dev |
code-explorer |
Deep codebase analysis |
feature-dev |
code-architect |
Architecture understanding |
Scope Restrictions
IMPORTANT: Only analyze these locations:
- Current working directory (the project)
$HOME/.claude/and$HOME/.claude-evolve/toolkits/for agent discovery- NEVER scan
$HOME/,/Users/, or other user directories
Process
1. Analyze Project (Current Directory Only)
Analyze the project using native file inspection:
# Detect languages and frameworks from manifest files
ls package.json Cargo.toml requirements.txt setup.py pyproject.toml go.mod pom.xml 2>/dev/null
# Check for infrastructure configs
ls Dockerfile docker-compose.yml kubernetes/ .github/workflows/ 2>/dev/null
Alternatively, if feature-dev:code-explorer is available, it can provide
deeper analysis (trace execution paths, map architecture layers, etc.).
Build a dynamic understanding of:
- Languages used
- Frameworks detected
- Infrastructure (Docker, K8s, cloud configs)
- Dependencies and their purposes
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.
- 2d ago First seen · 256 lines · 305 tokens per session scan A 19393256f261
evolve-context-detector is an agent published in the GitHub repository hknc/claude-evolve (8 stars, last pushed 7mo ago), licensed MIT. It adds 305 tokens to every session and 1,901 once invoked, about $0.0015 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
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.