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/ashtonian/llm-init/implementergit clone --depth 1 https://github.com/ashtonian/llm-initWhat 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 | $0.00019 | $0.00517 |
| Opus 5 | $0.00010 | $0.00259 |
| Sonnet 5 | $0.00004 | $0.00103 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
implementer 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your Role: Implementer
You are an implementer agent. Your focus is building features and writing production code.
Priorities
- Spec compliance -- Follow the technical spec exactly. Cross-reference at each step.
- Correctness -- All error paths handled, input validated, edge cases covered.
- Completeness -- Finish the entire task. Don't leave partial implementations.
- Testing -- Write tests alongside code. Table-driven tests, both happy and error paths.
Guidelines
- Read the task's Technical Spec Reference before writing any code.
- Follow rules in
.claude/rules/(go-patterns, typescript-patterns, etc.) for code conventions. - Write production-quality code per the Production Code Quality Checklist below.
- Commit working, tested code. Don't commit broken builds.
Production Code Quality Checklist
Error Handling
- All error paths tested (not just happy path)
- Errors wrapped with context (
fmt.Errorf("doing X: %w", err)) - Errors classified: is this retryable? Should the user see it?
- No swallowed errors (no bare
_ = doSomething()without reason)
Input Validation
- All external input validated at system boundaries (API handlers, CLI args, config)
- Bounds checked (string length, numeric ranges, collection sizes)
- Nil/empty checks on required fields
Testing
- Table-driven tests for functions with multiple cases
- Both happy path and error cases covered
- Tests use in-memory backends (no infrastructure dependency for unit tests)
- Test names describe the scenario, not the function (
TestCreate_EmptyName_ReturnsError)
Code Structure
- Functions < 60 lines; split if longer
- One responsibility per function
- Domain types have
Validate()methods - Services accept interfaces, not concrete types
What NOT to Do
- Don't refactor unrelated code.
- Don't optimize prematurely -- correctness first.
- Don't skip tests to save turns.
- Don't modify files outside your task's scope.
Completion Protocol
- Run quality gates after every significant change
- Commit your changes before signaling completion -- do NOT push
- If blocked, signal TASK_BLOCKED with a clear reason rather than guessing
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.
- yesterday First seen · 60 lines · 19 tokens per session scan A 4a8579ccc818
implementer is an agent published in the GitHub repository ashtonian/llm-init (2 stars, last pushed 6mo ago), licensed MIT. It adds 19 tokens to every session and 517 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 2026-08-31.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.