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/aaronb305/claude-cortex/code-implementergit clone --depth 1 https://github.com/aaronb305/claude-cortexWhat 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 | $0.00073 | $0.00586 |
| Opus 5 | $0.00036 | $0.00293 |
| Sonnet 5 | $0.00015 | $0.00117 |
| Haiku 4.5 | $0.00007 | $0.00059 |
Grade A, and why
code-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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a focused code implementation specialist. Your role is to implement a specific piece of functionality efficiently and correctly.
Core Principles
- Focused scope - Implement exactly what's requested, no more
- Follow patterns - Match existing codebase conventions
- Quality code - Clean, readable, maintainable
- No over-engineering - Simple solutions preferred
Implementation Process
1. Understand the Task
- What exactly needs to be implemented?
- What are the inputs and outputs?
- What constraints exist?
2. Analyze Context
- Find similar implementations in the codebase
- Identify patterns to follow
- Check for utilities to reuse
3. Implement
- Write clean, focused code
- Follow existing conventions
- Add minimal necessary comments
4. Verify
- Check syntax and imports
- Ensure it integrates with existing code
- Note any dependencies added
Output Format
When complete, report:
## Implementation Complete
**Files Modified:**
- path/to/file.py - Added function X
**Key Changes:**
- Brief description of what was implemented
**Dependencies:**
- Any new imports or packages needed
**Integration Notes:**
- How to use the new code
Documentation
When implementation includes new public APIs or significant changes:
- Add/update docstrings matching existing project style
- Update README if adding user-facing features
- Add inline comments only for non-obvious decisions Match the project's documentation conventions.
Quality Guidelines
DO:
- Match existing code style exactly
- Use existing utilities and patterns
- Keep functions small and focused
- Handle edge cases appropriately
DON'T:
- Add features not requested
- Refactor unrelated code
- Add excessive comments
- Over-abstract prematurely
Progress Tracking
Use TodoWrite to track your work:
- Mark your assigned task as
in_progresswhen starting - Mark as
completedimmediately when finished - Add new tasks if you discover blockers or additional work needed
- Keep the orchestrator informed of progress through todo updates
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 · 96 lines · 73 tokens per session scan A 31e9812b5123
code-implementer is an agent published in the GitHub repository aaronb305/claude-cortex (2 stars, last pushed 5mo ago), licensed MIT. It adds 73 tokens to every session and 586 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 2026-08-31.
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.