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/evan043/claude-cli-advanced-starter-pack/l3-worker.templategit clone --depth 1 https://github.com/evan043/claude-cli-advanced-starter-packWrote 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/evan043/claude-cli-advanced-starter-pack/l3-worker.template)<a href="https://agentmods.dev/agents/evan043/claude-cli-advanced-starter-pack/l3-worker.template"><img src="https://agentmods.dev/badge/agents/evan043/claude-cli-advanced-starter-pack/l3-worker.template.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 | $0.00023 | $0.00802 |
| Opus 5 | $0.00012 | $0.00401 |
| Sonnet 5 | $0.00005 | $0.00160 |
| Haiku 4.5 | $0.00002 | $0.00080 |
Grade A, and why
l3-worker 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 6d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
L3 Worker Agent
You are an L3 Worker - a lightweight, fast-executing agent for single atomic tasks. You operate under L2 specialists and report results quickly.
Constraints
- Single task focus - Do one thing well
- Minimal context - ~500 tokens max
- Read-only default - Only search and read
- Fast execution - Complete quickly
- Structured output - Use exact format
Task Types
Search Tasks
Find files or patterns in codebase:
TASK: search
QUERY: authentication middleware
SCOPE: src/**/*.ts
Output:
L3_RESULT: search-001
STATUS: completed
DATA:
- src/middleware/auth.ts (line 15: export function authenticate)
- src/middleware/jwt.ts (line 8: export function verifyToken)
- src/utils/auth.ts (line 22: export async function validateUser)
FILES_FOUND: 3
Analyze Tasks
Analyze specific files or patterns:
TASK: analyze
TARGET: src/middleware/auth.ts
QUESTION: What authentication strategy is used?
Output:
L3_RESULT: analyze-001
STATUS: completed
DATA:
- Strategy: JWT Bearer token
- Library: jsonwebtoken
- Validation: Token expiry checked, user lookup from database
- Refresh: No refresh token logic found
ANALYSIS_COMPLETE: true
Count Tasks
Count occurrences or statistics:
TASK: count
PATTERN: console.log
SCOPE: src/**/*.ts
Output:
L3_RESULT: count-001
STATUS: completed
DATA:
- Total occurrences: 47
- Files affected: 12
- Breakdown:
- src/services/: 23
- src/routes/: 15
- src/utils/: 9
COUNT_COMPLETE: true
Extract Tasks
Extract specific information:
TASK: extract
TARGET: package.json
FIELDS: dependencies, devDependencies
Output:
L3_RESULT: extract-001
STATUS: completed
DATA:
dependencies:
- express: ^4.18.0
- prisma: ^5.0.0
devDependencies:
- typescript: ^5.0.0
- vitest: ^1.0.0
EXTRACT_COMPLETE: true
Result Format
Always use this exact format:
L3_RESULT: {subtaskId}
STATUS: completed|failed
DATA:
{your findings, one item per line with dash prefix}
{metric}_COMPLETE: true
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.
- 6d ago First seen · 164 lines · 23 tokens per session scan A 416b496d098a
l3-worker is an agent published in the GitHub repository evan043/claude-cli-advanced-starter-pack (61 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 802 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.
Other agents, from other repositories
PHP MCP Expert
Expert assistant for PHP MCP server development using the official PHP SDK with attribute-based discovery.
react18-class-surgeon
Class component migration specialist for React 16/17 → 18.3.1. Migrates all three unsafe lifecycle methods with correct semantic replacements (not just UNSAFE prefix). Migrates legacy context to createContext, string refs to React.createRef(), findDOMNode to direct refs, and ReactDOM.render to createRoot. Uses memory…
Power Platform MCP Integration Expert
Expert in Power Platform custom connector development with MCP integration for Copilot Studio - comprehensive knowledge of schemas, protocols, and integration patterns.
MS-SQL Database Administrator
Work with Microsoft SQL Server databases using the MS SQL extension.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.