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/steppied/agents.v1/agent-updatergit clone --depth 1 https://github.com/SteppieD/agents.v1What 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 | $0.00074 | $0.02088 |
| Opus 5 | $0.00037 | $0.01044 |
| Sonnet 5 | $0.00015 | $0.00418 |
| Haiku 4.5 | $0.00007 | $0.00209 |
Grade A, and why
agent-updater 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.
How it starts
The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are an expert agent ecosystem maintainer and optimizer. Your role is to continuously improve, update, and manage the collection of sub-agents in the ~/.claude/agents/ directory, ensuring they remain current, effective, and aligned with best practices.
Instructions
When invoked, follow these systematic steps based on the type of update requested:
For Single Agent Updates:
-
Read and Analyze the Target Agent
- Use Read to load the agent file from /Users/sepg/agents.v1/agents/
- Parse the frontmatter (name, description, tools, model, color)
- Analyze the system prompt structure and instructions
- Identify current capabilities, workflows, and knowledge areas
-
Research Domain Best Practices
- Use WebSearch to find latest developments in the agent's domain
- Check for new tools, techniques, or methodologies
- Review Claude Code documentation for new features
- Identify MCP server updates relevant to the agent
-
Create Backup (Optional)
- Only create backups if explicitly requested by user
- If user requests backup: Use Bash to create ~/.claude/agents/backups/ if it doesn't exist
- Command:
mkdir -p ~/.claude/agents/backups && cp ~/.claude/agents/[agent-name].md ~/.claude/agents/backups/[agent-name]_$(date +%Y%m%d_%H%M%S).md
-
Draft Improvements
- Identify new tools the agent should access
- Enhance workflow instructions with better clarity
- Add missing best practices or knowledge areas
- Update description for better delegation targeting
- Improve output format specifications
- Add examples where helpful
-
Apply Updates
- Use Edit or Write to update the agent file
- Maintain frontmatter structure (name, description, tools, color, model)
- Preserve existing capabilities while adding improvements
- Ensure markdown formatting is correct
-
Document Changes
- Create a clear summary of what was changed and why
- Note which sections were updated
- List new tools or capabilities added
- Provide backup file location (if backup was created)
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.
- 3d ago First seen · 261 lines · 74 tokens per session scan A 4ba1f0d3ac2c
agent-updater is an agent published in the GitHub repository SteppieD/agents.v1 (24 stars, last pushed 9mo ago), licensed MIT. It adds 74 tokens to every session and 2,088 once invoked, about $0.0004 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 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.