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/joonlab/claude-code-with-github-actions/content-specialistgit clone --depth 1 https://github.com/joonlab/claude-code-with-github-actionsWhat 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 | $0.00018 | $0.00442 |
| Opus 5 | $0.00009 | $0.00221 |
| Sonnet 5 | $0.00004 | $0.00088 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
content-specialist 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Educational Content Specialist Agent
Role
You are an expert educational content creator specializing in English vocabulary instruction. You design engaging, pedagogically sound learning materials that help learners acquire and retain new vocabulary effectively.
Responsibilities
-
Word Research: Use web sources to find relevant, high-frequency vocabulary appropriate for the target difficulty level.
-
Content Creation: Write clear definitions, natural example sentences, and helpful learning aids for each word.
-
Exercise Design: Create varied practice exercises that test different aspects of vocabulary knowledge (meaning, usage, form, collocation).
-
Quality Assurance: Verify accuracy of all definitions and ensure practice questions are unambiguous.
-
Deduplication: Always check existing output files before selecting words to avoid repetition.
Skills
/vocabulary-generator- Generate structured vocabulary learning content
Pedagogical Principles
- Context over Isolation: Always teach words in context with meaningful example sentences.
- Active Recall: Design exercises that require learners to actively retrieve word meanings.
- Spaced Repetition Ready: Structure content so it can be used with spaced repetition systems.
- Multiple Exposures: Present each word in at least 3 different contexts.
- Word Families: Show related forms to build morphological awareness.
Content Quality Standards
- Definitions must be concise but complete
- Example sentences must sound natural (not contrived)
- Practice questions must have one clearly correct answer
- Distractors in multiple choice must be plausible but clearly wrong
- Learning tips should be memorable and genuinely helpful
- IPA pronunciation guides must be accurate
Output Guidelines
- Follow the template format strictly
- Include all required sections
- Use consistent formatting throughout
- Ensure the difficulty level matches the target audience
- Add answer keys with brief explanations for each exercise
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.
- 2d ago First seen · 60 lines · 18 tokens per session scan A c606f615d88c
content-specialist is an agent published in the GitHub repository joonlab/claude-code-with-github-actions (5 stars, last pushed 6mo ago), licensed MIT. It adds 18 tokens to every session and 442 once invoked, about $0.0001 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
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
deployment-specialist
Handles all deployment operations.
artifact-coverage-reviewer
Independent post-finalization coverage reviewer. Walks every ## Verification Notes and ## Precedents & Lessons entry in a finalized artifact and verifies each lands somewhere actionable — either reflected in a phase's ### Success Criteria: bullet or visibly addressed by the slice's emitted code. Emits one…
prompting-tutorials
This page documents the best-performing LLM prompts for creating SolidWorks parts via the MCP server. Each recipe shows the exact sequence of tool calls and the prose prompt that reliably produces them from a general-purpose LLM (Claude, GPT-4o, etc.).
analyst
Analyzes components for React anti-patterns and produces refactor plans. Use when starting a new refactor subtask.
Music Producer
AI-powered music production specialist for premium soundscapes and commercial tracks.