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 skills/docxology/template/srcnpx skills add docxology/template --skill srcgit clone --depth 1 https://github.com/docxology/templateWrote 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/docxology/template/src)<a href="https://agentmods.dev/skills/docxology/template/src"><img src="https://agentmods.dev/badge/skills/docxology/template/src.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 5.1 | $0.00019 | $0.00326 |
| Opus 5 | $0.00010 | $0.00163 |
| Sonnet 5 | $0.00004 | $0.00065 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
Meta-Analysis Source API 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.
What it actually says
Instructions
You are interfacing with the src/ directory of the literature meta-analysis project. This directory contains 45+ public APIs spread across 6 submodules.
Agentic Interface (MCP Strategy)
When operating within this workspace, adhere to the following interaction protocols:
- No-Mock Constraint: If you write tests for these modules, you MUST use
pytest-httpserveror local data objects. Do not usemocker.patchorMagicMock. - Execution Context: Execute modules using the thin orchestrators located in
scripts/, or by runninguv run pytestin thetests/directory. Do not write temporary execution blocks insidesrc/. - Data Immutability: The code here processes JSONL and TriG outputs. Ensure you have parsed
manuscript/config.yamlusing your file reading tools to understand runtime constraints.
Architecture Guidelines for AI Agents
- Modularity: Business logic never resides in
scripts/. It belongs here. - Reproducibility: When adding new NLP or analytical functions, ensure RNG seeds are hardcoded (typically
seed=42) to guarantee deterministic analysis. - Documentation Parity: If you modify any file here, you must run
python3 -m infrastructure.validation.cli markdownto verify nothing was broken.
Refer to the specific SKILL.md in each subdirectory for granular file-level guidance.
What ships with it
60 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.
- __init__.py 346 B runs code
- AGENTS.md 3.0 KB
- analysis/__init__.py 917 B runs code
- analysis/AGENTS.md 3.6 KB
- analysis/citation_network.py 11 KB runs code
- analysis/descriptive_stats.py 8.3 KB runs code
- analysis/embeddings.py 5.7 KB runs code
- analysis/entities.py 9.6 KB runs code
- analysis/pipeline_runner.py 11 KB runs code
- analysis/README.md 4.2 KB
- analysis/SKILL.md 958 B
- analysis/subfield_classifier.py 2.9 KB runs code
- analysis/subfield_defaults.py 760 B runs code
- analysis/subfield_registry.py 10 KB runs code
- analysis/temporal_analysis.py 5.9 KB runs code
- analysis/text_processing.py 5.9 KB runs code
- analysis/topic_modeling.py 5.8 KB runs code
- config_loader.py 6.9 KB runs code
- config_validation.py 15 KB runs code
- config.py 5.2 KB runs code
- deep_research/__init__.py 447 B runs code
- deep_research/AGENTS.md 2.0 KB
- deep_research/deep_research_adapter.py 5.7 KB runs code
- deep_research/fixtures/AGENTS.md 397 B
- deep_research/fixtures/README.md 382 B
- deep_research/fixtures/recorded_report.json 2.5 KB
- deep_research/README.md 2.4 KB
- knowledge_graph/__init__.py 929 B runs code
- knowledge_graph/AGENTS.md 4.1 KB
- knowledge_graph/calibration.py 3.1 KB runs code
- knowledge_graph/extraction.py 2.0 KB runs code
- knowledge_graph/graph_builder.py 10 KB runs code
- knowledge_graph/hypothesis.py 11 KB runs code
- knowledge_graph/kg_runner.py 8.7 KB runs code
- knowledge_graph/llm_client.py 3.5 KB runs code
- knowledge_graph/llm_config.py 551 B runs code
- knowledge_graph/llm_extraction.py 7.4 KB runs code
- knowledge_graph/llm_prompts.py 1.6 KB runs code
- knowledge_graph/nanopublication.py 14 KB runs code
- knowledge_graph/query.py 3.5 KB runs code
- knowledge_graph/README.md 3.9 KB
- knowledge_graph/schema.py 3.4 KB runs code
- knowledge_graph/SKILL.md 1.0 KB
- literature/__init__.py 662 B runs code
- literature/AGENTS.md 6.8 KB
- literature/arxiv_client.py 9.0 KB runs code
- literature/bibliography.py 13 KB runs code
- literature/biorxiv_client.py 11 KB runs code
- literature/corpus.py 10 KB runs code
- literature/crossref_client.py 12 KB runs code
- literature/engine_dispatch.py 2.8 KB runs code
- literature/europepmc_client.py 8.8 KB runs code
- literature/evaluation.py 5.4 KB runs code
- literature/fixture_corpus.py 8.4 KB runs code
- literature/fixture_honesty.py 3.8 KB runs code
- literature/fulltext_assessment.py 9.3 KB runs code
- literature/fulltext_download_cli.py 5.8 KB runs code
- literature/fulltext_download.py 15 KB runs code
- literature/http.py 3.0 KB runs code
- literature/models.py 11 KB runs code
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 · 25 lines · 19 tokens per session scan A 8ee574b5ce81
Meta-Analysis Source API is a skill published in the GitHub repository docxology/template (19 stars, last pushed yesterday), licensed Apache-2.0. It adds 19 tokens to every session and 326 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 2026-09-03.
Other skills, from other repositories
bioinformatics-scientist
Use when a task needs the judgment of a Bioinformatics Scientist — designing a differential-expression or GWAS analysis with correct multiple-testing correction, calling and triaging variants from NGS data using genotype-likelihood confidence rather than raw allele counts, interpreting a BLAST/DIAMOND homology search…
shipjaw-prompt
Turns a rough, messy, or vague product idea into a dense build-ready product prompt and persists it at documentation/product/source-prompt.md for shipjaw-build. Use when the user wants to express/clarify/polish a product before scaffolding, mentions idée vague, brainstorm app, help me write the prompt, notes produit…
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
9router
Entry point for 9Router — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions 9Router, NINEROUTERURL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant capability…
best-practices
Transforms vague prompts into optimized Claude Code prompts. Adds verification, specific context, constraints, and proper phasing. Invoke with /best-practices.
mongodb-search-and-ai
Guides MongoDB users through implementing and optimizing Atlas Search (full-text), Vector Search (semantic), and Hybrid Search solutions. Use this skill when users need to build search functionality for text-based queries (autocomplete, fuzzy matching, faceted search), semantic similarity (embeddings, RAG…