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 opencue/cuecards --skill claude-apigit clone --depth 1 https://github.com/opencue/cuecardsWrote 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/opencue/cuecards/claude-api)<a href="https://agentmods.dev/skills/opencue/cuecards/claude-api"><img src="https://agentmods.dev/badge/skills/opencue/cuecards/claude-api/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/opencue/cuecards/claude-api"><img src="https://agentmods.dev/badge/skills/opencue/cuecards/claude-api.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 266 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Excessive Agency · line 328 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00294 | $0.08698 |
| Opus 5.5 | $0.00118 | $0.03479 |
| Sonnet 5.5 | $0.00059 | $0.01740 |
| Haiku 4.5 | $0.00029 | $0.00870 |
Grade A, and why
Codex-api scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. **Raw HTTP** (`curl`, `requests`, `fetch`, `httpx`, etc.) — only when the user explicitly asks for cURL/REST/raw HTTP, the project is a shell/cURL project, or the language has no official SDK. How it starts
The opening of the file, as written. The whole thing — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building LLM-Powered Applications with Codex
This skill helps you build LLM-powered applications with Codex. Choose the right surface based on your needs, detect the project language, then read the relevant language-specific documentation.
Before You Start
Scan the target file (or, if no target file, the prompt and project) for non-Anthropic provider markers — import openai, from openai, langchain_openai, OpenAI(, gpt-4, gpt-5, file names like agent-openai.py or *-generic.py, or any explicit instruction to keep the code provider-neutral. If you find any, stop and tell the user that this skill produces Codex/Anthropic SDK code; ask whether they want to switch the file to Codex or want a non-Codex implementation. Do not edit a non-Anthropic file with Anthropic SDK calls.
Output Requirement
When the user asks you to add, modify, or implement a Codex feature, your code must call Codex through one of:
- The official Anthropic SDK for the project's language (
anthropic,@anthropic-ai/sdk,com.anthropic.*, etc.). This is the default whenever a supported SDK exists for the project. - Raw HTTP (
curl,requests,fetch,httpx, etc.) — only when the user explicitly asks for cURL/REST/raw HTTP, the project is a shell/cURL project, or the language has no official SDK.
Never mix the two — don't reach for requests/fetch in a Python or TypeScript project just because it feels lighter. Never fall back to OpenAI-compatible shims.
Never guess SDK usage. Function names, class names, namespaces, method signatures, and import paths must come from explicit documentation — either the {lang}/ files in this skill or the official SDK repositories or documentation links listed in shared/live-sources.md. If the binding you need is not explicitly documented in the skill files, WebFetch the relevant SDK repo from shared/live-sources.md before writing code. Do not infer Ruby/Java/Go/PHP/C# APIs from cURL shapes or from another language's SDK.
What ships with it
47 files 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.
- csharp/claude-api.md 15 KB
- curl/examples.md 6.3 KB
- curl/managed-agents.md 7.3 KB
- go/claude-api.md 14 KB
- go/managed-agents/README.md 18 KB
- java/claude-api.md 15 KB
- java/managed-agents/README.md 16 KB
- LICENSE.txt 11 KB
- php/claude-api.md 12 KB
- php/managed-agents/README.md 13 KB
- python/claude-api/batches.md 5.5 KB
- python/claude-api/files-api.md 4.3 KB
- python/claude-api/README.md 16 KB
- python/claude-api/streaming.md 5.9 KB
- python/claude-api/tool-use.md 17 KB
- python/managed-agents/README.md 9.8 KB
- ruby/claude-api.md 3.4 KB
- ruby/managed-agents/README.md 9.9 KB
- shared/agent-design.md 8.3 KB
- shared/anthropic-cli.md 16 KB
- shared/claude-platform-on-aws.md 3.9 KB
- shared/error-codes.md 8.7 KB
- shared/live-sources.md 18 KB
- shared/managed-agents-api-reference.md 24 KB
- shared/managed-agents-client-patterns.md 9.2 KB
- shared/managed-agents-core.md 15 KB
- shared/managed-agents-environments.md 11 KB
- shared/managed-agents-events.md 9.4 KB
- shared/managed-agents-memory.md 9.4 KB
- shared/managed-agents-multiagent.md 6.4 KB
- shared/managed-agents-onboarding.md 13 KB
- shared/managed-agents-outcomes.md 6.0 KB
- shared/managed-agents-overview.md 10 KB
- shared/managed-agents-self-hosted-sandboxes.md 9.7 KB
- shared/managed-agents-tools.md 14 KB
- shared/managed-agents-webhooks.md 4.9 KB
- shared/model-migration.md 82 KB
- shared/models.md 8.1 KB
- shared/prompt-caching.md 14 KB
- shared/token-counting.md 1.6 KB
- shared/tool-use-concepts.md 17 KB
- typescript/claude-api/batches.md 2.5 KB
- typescript/claude-api/files-api.md 2.2 KB
- typescript/claude-api/README.md 12 KB
- typescript/claude-api/streaming.md 5.5 KB
- typescript/claude-api/tool-use.md 15 KB
- typescript/managed-agents/README.md 9.3 KB
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.
- 2mo ago First seen · 336 lines · 294 tokens per session scan A 98be174cb5ad
Codex-api is a skill published in the GitHub repository opencue/cuecards (7 stars, last pushed yesterday), licensed MIT. It adds 294 tokens to every session and 8,698 once invoked, about $0.0012 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Codex-api compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Codex-apiopencue/cuecards | Skill | 7 | yesterday | MIT | A | 294 | Claude Code, Codex |
| agentloop-audit-queryalibaba/loongsuite-pilot | Skill | 239 | yesterday | Apache-2.0 | A | 114 | Claude Code, Codex |
| loongsuite-pilot-insightalibaba/loongsuite-pilot | Skill | 239 | yesterday | Apache-2.0 | A | 111 | Claude Code, Codex |
| loongsuite-pilot-opsalibaba/loongsuite-pilot | Skill | 239 | yesterday | Apache-2.0 | A | 15 | Claude Code, Codex |
| atomic-visual-optionsdamusix/atomic-claude | Skill | 115 | 5d ago | MIT | A | 150 | Claude Code, Codex |
| atomic-wikidamusix/atomic-claude | Skill | 115 | 5d ago | MIT | A | 204 | Claude Code, Codex |
| atomic-reviewdamusix/atomic-claude | Skill | 115 | 5d ago | MIT | A | 63 | Claude Code, Codex |