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 skills add joao-aires/agent-skills-public --skill ai-conventionsgit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/skills/joao-aires/agent-skills-public/ai-conventions)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/ai-conventions"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/ai-conventions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/ai-conventions"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/ai-conventions.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00038 | $0.00729 |
| Opus 5.5 | $0.00015 | $0.00292 |
| Sonnet 5.5 | $0.00008 | $0.00146 |
| Haiku 4.5 | $0.00004 | $0.00073 |
Grade A, and why
ai-conventions 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply the selected AI stack
Use AI contract and evaluation expertise when available for task contracts, authority and evaluation; otherwise retain explicit success/failure, authorization and quality evidence in the application. This guidance owns technical defaults and integration choices, not product scope or quality commitments. Preserve an accepted provider/framework unless changing it is requested or a consequential decision is reopened.
Implement the accepted provider boundary
Use the application's Python adapter and locked, compatible SDK version. Framework choice belongs to the accepted architecture: use installed ADK or LangChain/LangGraph specialists only for that chosen framework, without introducing either family for a direct SDK call. Keep provider configuration and credentials at the integration boundary. Translate the SDK's responses into the application's own result and failure semantics there, including incomplete output, refusals, tool requests and transport errors. Domain code should not need to infer success from provider-specific response fields.
For streaming, decide how the application assembles partial output, signals completion and handles interruption. Verify the selected SDK's actual lifecycle rather than assuming a stream of text has the same contract as a complete response. Preserve enough operation identity to diagnose a retry without repeating a consequential tool action.
Prefer Gemini for low-cost LLM and transcription experiments.
- Verify current capabilities, quota, pricing and data-handling terms for the selected model/account before live use; free-tier eligibility is not a promise that all calls are free.
- Keep settings and credentials in configuration and domain behavior testable without the provider.
- Uploaded-audio transcription and streaming voice need different implementations and evidence.
Implement Python MCP with version-matched APIs
Use installed mcp-builder for protocol implementation when available.
- Prefer Python and standalone fastmcp (
uv add fastmcp,from fastmcp import FastMCP) with a tested compatible production version. - Its API differs from the MCP SDK's mcp.server.fastmcp; check Context, lifecycle, authentication and transport against the selected standalone version.
- Preserve an existing server until migration is in scope.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +20 lines 35612af3913d
- 2d ago First seen · 33 lines · 38 tokens per session scan A 4211732986dd
ai-conventions is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 729 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-20.
Other skills, from other repositories
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
finetuning
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file…