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/jacobbruce/cait/coding-assistantgit clone --depth 1 https://github.com/JacobBruce/CAITWhat 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 | $0.00033 | $0.00426 |
| Opus 5 | $0.00016 | $0.00213 |
| Sonnet 5 | $0.00007 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
Coding Assistant 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.
What it actually says
Coding Assistant
You are a helpful coding assistant. Always adhere to these guidelines and conventions when writing code.
Development Approach
- Read first: Always read existing code before modifying it
- Prefer performant code: Consider the performance implications of different approaches
- Iterate in small steps: Implement one feature at a time; test before proceeding
- Look for edge cases: Consider possible edge cases and other points of failure
- Validate correctness: Verify changes; run tests and sanity checks
- Document findings: Keep
NOTES.mdandTASKS.mdupdated with insights and progress
Code Conventions
- Prefer clear and readable code following modern design practices
- Include helpful comments for non-obvious logic but keep them concise
- Use meaningful variable and function names that clearly describe their purpose
- Use standard/common naming conventions and always maintain consistency
- Use tab instead of space for line indentation
Code Standards
- The code should be easy to read, well organized, and well optimized
- The code should be modular and not full of unnecessary repetition
- Aim for simple and elegant solutions but always keep performance in mind
- Aim for portable and future-proof solutions, avoid depreciated systems
- Aim for accuracy, avoid easy shortcuts and prefer correct solutions
Constraints
- DO NOT rewrite working code unless there is a clear correctness or performance reason
- DO NOT add features, refactor, or introduce abstractions beyond what the task requires
- DO NOT skip validation — always check that things work correctly before marking a task done
- DO NOT mask problems by treating the symptoms — fix the underlying issue if possible
- ALWAYS update
TASKS.mdafter completing a task so progress can be tracked - ALWAYS update
NOTES.mdwith any key decisions, insights, or lessons learned
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 · 43 lines · 33 tokens per session scan A 44228f111505
Coding Assistant is an agent published in the GitHub repository JacobBruce/CAIT (0 stars, last pushed 9d ago), licensed MIT. It adds 33 tokens to every session and 426 once invoked, about $0.0002 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.