agentmods.dev

infrastructure-overview

A guide to the reusable infrastructure layer in a research codebase. It explains how shared modules and project-specific code fit together, and how agents can find and use them.

In plain words
What is it for?
Use it when editing the infrastructure/ folder, importing modules, discovering available skills, or connecting build, validation, rendering, and publishing steps.
Why use it?
It removes the need to guess where code belongs or how the project’s two layers connect. It also helps prevent scripts from duplicating logic that should live in shared modules.

Skill for Claude CodeCodex

19 2d ago A scan 80 tokens original Apache-2.0
View the source file docxology/template
Install

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.

agentmods
npx agentmods add skills/docxology/template/infrastructure
Any agent
npx skills add docxology/template --skill infrastructure
Clone the repo
git clone --depth 1 https://github.com/docxology/template

Made for: Claude Code, Codex.

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,004 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00080 $0.02004
Opus 5 $0.00040 $0.01002
Sonnet 5 $0.00016 $0.00401
Haiku 4.5 $0.00008 $0.00200

Measured 2d ago against content hash ab2008e45e19, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

infrastructure-overview 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.

The scan reads SKILL.md. This mod also ships 43 executable files (__init__.py, autoresearch/__init__.py, autoresearch/__main__.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

infrastructure/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Infrastructure Layer

The infrastructure/ package provides generic, reusable functionality for research projects. All business logic resides here (Layer 1) or in project-specific src/ (Layer 2). Scripts are thin orchestrators that coordinate these modules.

Finding skills (Cursor and other agents)

  • Hub: This file lists every subpackage skill and a module map.
  • Manifest: .cursor/skill_manifest.json lists every discovered first-party skill (name, description, path); regenerate with uv run python -m infrastructure.skills write.
  • Search: default discovery covers infrastructure/**/SKILL.md, scripts/**/SKILL.md, public projects/templates/**/SKILL.md including .agents/skills, public resource-pool template skills under fonds/templates/, rules/templates/, and tools/templates/, plus .cursor/skills/.
  • In Cursor: @infrastructure/SKILL.md or @infrastructure/<module>/SKILL.md to load context; pair with the matching AGENTS.md for API tables.
  • Frontmatter: Each SKILL.md has YAML name and description for routing (see also the table in infrastructure/README.md).

Module Map

Module Purpose Key Imports
autoresearch/ Deterministic research plans, stage-gate readiness, artifact/evidence reports build_autoresearch_plan, validate_autoresearch_plan
benchmark/ Deterministic benchmark manifests and public exemplar readiness scoring run_benchmark_manifest, score_project_against_manifest
config/ Repo defaults (.env.template, secure_config.yaml) (YAML/dotenv; use core.config_loader)
core/ Logging, config, exceptions, pipeline, progress, retry, security get_logger, load_config, PipelineExecutor
docker/ Dockerfile, docker-compose.yml for container runs (CLI / docs/CLOUD_DEPLOY.md)
validation/ PDF/Markdown/output validation, link checking, audits validate_pdf_rendering, validate_markdown, verify_output_integrity
rendering/ Multi-format output (PDF, HTML, slides) RenderManager, RenderingConfig
documentation/ Figure/image management, markdown integration, glossary FigureManager, ImageManager, MarkdownIntegration
llm/ Local LLM integration via Ollama LLMClient, OllamaClientConfig, detect_repetition, check_format_compliance
methods/ Methods orchestration plans over DAG, manuscript methods, artifacts, and evidence build_methods_orchestration_plan, validate_methods_orchestration_plan
orchestration/ Pipeline CLI, menu, project discovery, stage logging, secure-run wrapper (backs run.sh/secure_run.sh) build_parser, PipelineRunner, validate_project_slug, run_secure_pipeline
publishing/ Academic publishing (DOI, citations, Zenodo, arXiv) publish_to_zenodo, generate_citation_bibtex
reference/ BibTeX I/O (read / write / convert) matching references.bib syntax parse_bibfile, render_database, paper_to_bibentry
search/ Paperclip-style multi-source literature search (arXiv, Crossref, local, Paperclip) LiteratureClient, SearchQuery, ArxivBackend, CrossrefBackend
prose/ Prose analysis (readability, structure, editorial quality, manuscript reports) analyze_manuscript, compute_metrics, analyze_structure, analyze_quality
reporting/ Pipeline reports, error aggregation, dashboards generate_pipeline_report, get_error_aggregator
scientific/ Benchmarking, numerical stability, scientific templates benchmark_function, check_numerical_stability
sia/ SIA harness: task layout, fixture replay loop, evaluation runner validate_task_dir, run_sia_loop, run_evaluation
project/ Multi-project discovery and validation discover_projects, validate_project_structure
skills/ Enumerate and parse SKILL.md; maintain Cursor manifest discover_skills, write_skill_manifest
steganography/ Cryptographic PDF watermarking and verification SteganographyProcessor, SteganographyConfig, embed_steganography
core/telemetry/ Unified pipeline telemetry (stage resources + diagnostics, JSON/text reports) TelemetryCollector, TelemetryConfig

Read the full file on GitHub · 124 lines

Files

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.

Changes

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.

  1. 2d ago First seen · 124 lines · 80 tokens per session scan A ab2008e45e19

Subscribe to this mod's changes

infrastructure-overview is a skill published in the GitHub repository docxology/template (19 stars, last pushed 2d ago), licensed Apache-2.0. It adds 80 tokens to every session and 2,004 once invoked, about $0.0004 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 2026-08-30.

LaTeXPlanningResearchagents-mdai-agentsclaude-codecomputational-researchcursor
Related

Other skills, from other repositories

browser-trace

Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-progress session, or feed structured per-page…

mxyhi/ok-skills · 88 tokens

planning-with-files

Manus-style persistent file-based planning for AI coding agents: keeps taskplan.md, findings.md, and progress.md on disk so work survives context loss and /clear. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring 5+ tool calls. Supports automatic session…

mxyhi/ok-skills · 76 tokens

ai-elements

Build AI chat interfaces using ai-elements components — conversations, messages, tool displays, prompt inputs, and more. Use when the user wants to build a chatbot, AI assistant UI, or any AI-powered chat interface.

mxyhi/ok-skills · 46 tokens

exa-search

Use Exa MCP for current web, code/docs, company, people, and page-fetch research. Prefer current hosted tool schemas and note deprecated tools.

mxyhi/ok-skills · 33 tokens

ontoly-software-graph

Use Ontoly's deterministic Software Graph and MCP capabilities for repository architecture, request tracing, dependency analysis, configuration lookup, and impact analysis before falling back to source search.

mxyhi/ok-skills · 40 tokens

kimi-webbridge

Kimi WebBridge lets AI control the user's real browser — navigate, click, type, read, screenshot, and interact with any website using the user's actual login sessions. Use this skill whenever the user wants to interact with websites, automate browser tasks, scrape web content, or perform any action requiring a real…

mxyhi/ok-skills · 113 tokens