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 commands/christopherlouet/claude-base/dev-ai-integrationgit clone --depth 1 https://github.com/christopherlouet/claude-baseWrote 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/commands/christopherlouet/claude-base/dev-ai-integration)<a href="https://agentmods.dev/commands/christopherlouet/claude-base/dev-ai-integration"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/dev-ai-integration.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 | $0.00000 | $0.00443 |
| Opus 5 | $0.00000 | $0.00221 |
| Sonnet 5 | $0.00000 | $0.00089 |
| Haiku 4.5 | $0.00000 | $0.00044 |
Grade A, and why
dev-ai-integration 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 4d 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.
What it actually says
Agent DEV-AI-INTEGRATION
Integration of language models (LLM) and AI APIs into applications.
Request context
$ARGUMENTS
Objective
Integrate LLM APIs (Anthropic, OpenAI, Google, Mistral, Cohere) into an application with security, performance, and monitoring best practices.
Workflow
- Choose the provider and model based on the use case (cost, performance, features)
- Implement the appropriate pattern: simple completion, streaming, tool use/function calling, RAG
- Add error handling with retry and exponential backoff
- Implement rate limiting (Bottleneck or equivalent)
- Add caching (Redis or equivalent) for repeated requests
- Secure: environment variables for API keys, input sanitization, user/system separation
- Configure monitoring: latency (<5s), tokens/request, cost/day, error rate (<1%)
Expected output
Integration plan with chosen provider, architecture, files to create/modify, cost estimation, and risks with mitigations.
Related agents
| Agent | Usage |
|---|---|
/dev:dev-rag |
RAG systems |
/dev:dev-api |
API endpoints |
/ops:ops-monitoring |
Production monitoring |
See also (vendor depth)
This command stays the neutral multi-provider layer (choosing among Anthropic/OpenAI/Google/Mistral/Cohere — a chooser no single vendor can own without bias). For Claude-specific integration depth (single-call vs tool-use loop vs managed agents, streaming, prompt caching, token counting, model migration, across 8 languages), pair it with the claude-api skill — Anthropic's own, already bundled in Claude Code. See docs/recipes/recommended-vendor-skills.md §"Anthropic — claude-api".
IMPORTANT: Always use environment variables for API keys.
IMPORTANT: Never log prompts containing user data.
YOU MUST implement rate limiting and retry logic.
NEVER expose API keys in source code.
Think hard about model choice and cost estimation.
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.
- 4d ago First seen · 51 lines · 0 tokens per session scan A 9daf29bc718e
dev-ai-integration is a command published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 443 tokens. 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 commands, from other repositories
plan
Execute the implementation planning workflow using the plan template to generate design artifacts.
specify
Create or update the feature specification from a natural language feature description.
registry
Discover, create, or update the Project Defaults Registry. Scans project manifests (package.json, pyproject.toml, Cargo.toml, go.mod, etc.), batches findings for HITL confirmation, then writes specs/defaults/registry.yaml with a full audit trail in changelog.md.
taskstoissues
Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.
_subagent-discovery
Whenever a command needs to pick a subagent for a task (planning, task generation, or implementation execution). Do not hardcode agent names in command templates. Do not assume a specific agent exists.
CONTEXT
Slash commands for SPEC-First development workflow.