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 zebbern/termstack --skill claude-apigit clone --depth 1 https://github.com/zebbern/termstackWrote 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/zebbern/termstack/claude-api)<a href="https://agentmods.dev/skills/zebbern/termstack/claude-api"><img src="https://agentmods.dev/badge/skills/zebbern/termstack/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/zebbern/termstack/claude-api"><img src="https://agentmods.dev/badge/skills/zebbern/termstack/claude-api.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 | $0.00084 | $0.04443 |
| Opus 5 | $0.00042 | $0.02221 |
| Sonnet 5 | $0.00017 | $0.00889 |
| Haiku 4.5 | $0.00008 | $0.00444 |
Grade A, and why
claude-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 7d 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.
- Suggest cURL/raw HTTP examples from `curl/` and note that community SDKs may exist The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
51 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 1.7 KB
- csharp/claude-api.mdZone.Identifier 25 B
- curl/examples.md 4.4 KB
- curl/examples.mdZone.Identifier 25 B
- go/claude-api.md 3.9 KB
- go/claude-api.mdZone.Identifier 25 B
- java/claude-api.md 3.8 KB
- java/claude-api.mdZone.Identifier 25 B
- LICENSE.txt 11 KB
- LICENSE.txtZone.Identifier 25 B
- php/claude-api.md 1.5 KB
- php/claude-api.mdZone.Identifier 25 B
- python/agent-sdk/patterns.md 8.0 KB
- python/agent-sdk/patterns.mdZone.Identifier 25 B
- python/agent-sdk/README.md 9.6 KB
- python/agent-sdk/README.mdZone.Identifier 25 B
- python/claude-api/batches.md 4.8 KB
- python/claude-api/batches.mdZone.Identifier 25 B
- python/claude-api/files-api.md 3.8 KB
- python/claude-api/files-api.mdZone.Identifier 25 B
- python/claude-api/README.md 11 KB
- python/claude-api/README.mdZone.Identifier 25 B
- python/claude-api/streaming.md 5.1 KB
- python/claude-api/streaming.mdZone.Identifier 25 B
- python/claude-api/tool-use.md 16 KB
- python/claude-api/tool-use.mdZone.Identifier 25 B
- ruby/claude-api.md 1.8 KB
- ruby/claude-api.mdZone.Identifier 25 B
- shared/error-codes.md 6.9 KB
- shared/error-codes.mdZone.Identifier 25 B
- shared/live-sources.md 10 KB
- shared/live-sources.mdZone.Identifier 25 B
- shared/models.md 4.5 KB
- shared/models.mdZone.Identifier 25 B
- shared/tool-use-concepts.md 14 KB
- shared/tool-use-concepts.mdZone.Identifier 25 B
- SKILL.mdZone.Identifier 25 B
- typescript/agent-sdk/patterns.md 3.2 KB
- typescript/agent-sdk/patterns.mdZone.Identifier 25 B
- typescript/agent-sdk/README.md 7.7 KB
- typescript/agent-sdk/README.mdZone.Identifier 25 B
- typescript/claude-api/batches.md 2.5 KB
- typescript/claude-api/batches.mdZone.Identifier 25 B
- typescript/claude-api/files-api.md 2.2 KB
- typescript/claude-api/files-api.mdZone.Identifier 25 B
- typescript/claude-api/README.md 8.4 KB
- typescript/claude-api/README.mdZone.Identifier 25 B
- typescript/claude-api/streaming.md 5.5 KB
- typescript/claude-api/streaming.mdZone.Identifier 25 B
- typescript/claude-api/tool-use.md 13 KB
- typescript/claude-api/tool-use.mdZone.Identifier 25 B
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.
- 7d ago First seen · 257 lines · 84 tokens per session scan A 0fcad99e2333
claude-api is a skill published in the GitHub repository zebbern/termstack (5 stars, last pushed 4mo ago), with no licence file. It adds 84 tokens to every session and 4,443 once invoked, about $0.0004 per session on Opus 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 2026-09-03.
Other skills, from other repositories
slime-rl-training
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
huawei-modelarts
Use when training, deploying, or managing AI/ML models on Huawei Cloud ModelArts. Covers training jobs, model registry, online services, notebook instances. Triggers: ModelArts, model training, AI, machine learning, deep learning, notebook, inference, deployment. NOT for: general AI/ML concepts, non-Huawei platforms.
grad-ai-ethics
Apply AI ethics frameworks (fairness, accountability, transparency, privacy) to evaluate AI systems for algorithmic bias, explainability gaps, and value alignment failures. Use this skill when the user needs to audit an AI system for ethical risks, design fairness constraints, assess explainability requirements, or…
algo-nlp-lda
Implement LDA topic modeling to discover latent topics in document collections. Use this skill when the user needs to extract topics from a text corpus, categorize documents by theme, or explore thematic structure — even if they say 'what are the main topics', 'topic extraction', or 'document clustering by theme'.
algo-nlp-ner
Implement Named Entity Recognition to identify and classify entities in text. Use this skill when the user needs to extract people, organizations, locations, dates, or custom entities from documents — even if they say 'extract names from text', 'find companies mentioned', or 'entity extraction'.
algo-nlp-similarity
Calculate text similarity using lexical and semantic methods for matching and deduplication. Use this skill when the user needs to find similar documents, detect near-duplicates, or measure semantic closeness between texts — even if they say 'how similar are these texts', 'find duplicates', or 'semantic matching'.