agentmods.dev

access-to CLAUDE.md

access-to CLAUDE.md is an instructions file for coding agents from dougdevitre/access-to. It costs 612 tokens per session, scanned A, original, MIT.

Instructions for working in the Access To repository, a hub that manages a collection of open-source Claude skills. They describe the repository layout, configuration files, and maintenance scripts.

In plain words
What is it for?
They support validating configuration, syncing repositories, labels, issue templates, and health checks, plus onboarding child repositories.
Why use it?
They help agents follow the project's source-of-truth files, shared logging rules, validation checks, and repository-management workflow.

Instructions file

not rated 1 2mo ago A scan 612 tokens original MIT
View the source file dougdevitre/access-to
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 instructions/dougdevitre/access-to/claude-md
Clone the repo
git clone --depth 1 https://github.com/dougdevitre/access-to

Wrote 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.

agentmods badge for access-to CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dougdevitre/access-to/claude-md.svg)](https://agentmods.dev/instructions/dougdevitre/access-to/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dougdevitre/access-to/claude-md"><img src="https://agentmods.dev/badge/instructions/dougdevitre/access-to/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 612 This file is loaded in full into every session.
When invoked 612 The same file — it is already loaded in full.
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 $0.00612 $0.00612
Opus 5 $0.00306 $0.00306
Sonnet 5 $0.00122 $0.00122
Haiku 4.5 $0.00061 $0.00061

Measured 3d ago against content hash e0a806f56b07, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

access-to CLAUDE.md 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 3d 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.

CLAUDE.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Instructions for Claude Code

Project overview

Access To is a hub-and-spokes ecosystem of open-source Claude Skills. This repo is the hub — it contains the landing site and the admin system that orchestrates all child repos.

Repository structure

.github/
├── config/repos.json       # Source of truth for all repos (name, pillar, scope, connections)
├── config/labels.json       # Shared label taxonomy synced to all repos
├── schemas/                 # JSON Schemas for config validation
├── scripts/                 # Admin scripts (all source lib-log.sh)
│   ├── lib-log.sh           # Shared logging library (always use this, never raw echo)
│   ├── validate-config.sh   # Config integrity checks
│   ├── sync-repos.sh        # Sync repos → GitHub Project
│   ├── sync-labels.sh       # Push labels → all repos
│   ├── sync-templates.sh    # Push issue templates → child repos
│   ├── health-check.sh      # Ecosystem dashboard
│   └── onboard-repo.sh      # New repo setup
├── workflows/               # GitHub Actions (thin orchestration calling scripts)
└── ISSUE_TEMPLATE/          # Shared issue templates

Root files are the static landing site (HTML/CSS, vanilla JS, no build step).

Commands

# Validate config files
.github/scripts/validate-config.sh .github/config

# Test validation in JSON log mode
LOG_FORMAT=json .github/scripts/validate-config.sh .github/config

# Onboard a new repo
.github/scripts/onboard-repo.sh <repo-name> <pillar> [scope]

# View the site locally
open index.html

Rules

  • No frameworks. HTML/CSS/JS only for the site. No npm, no bundlers.
  • Config-driven. Never hardcode repo lists. Read from repos.json.
  • Structured logging. Source lib-log.sh in all scripts. Use log_info, log_warn, log_error, log_action.
  • Schema-validated. Config changes must pass validate-config.sh. Run it before committing.
  • Accessible. All HTML must include ARIA labels, work with keyboard navigation, and support dark mode.
  • Idempotent. All sync scripts must be safe to re-run.
  • Exit codes matter. Scripts exit 1 on errors — don't mask failures.
  • When editing repos.json, valid pillars are: hub, housing, jobs, health, business, services, education, safety. Valid scopes: missouri, nationwide, global. Valid roles: hub, pillar, tool, docs.
  • connects_to entries must reference repo names that exist in the registry.

Read the full file on GitHub · 55 lines

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. 3d ago First seen · 55 lines · 612 tokens per session scan A e0a806f56b07

Subscribe to this mod's changes

access-to CLAUDE.md is an instructions file published in the GitHub repository dougdevitre/access-to (1 stars, last pushed 2mo ago), licensed MIT. It adds 612 tokens to every session, about $0.0031 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.

access-to-justiceai-toolsanthropiccivic-techclaude-aiclaude-skill
Related

Other instructions, from other repositories

Skill_Seekers CLAUDE.md

Instructions for yusufkaraaslan/Skill_Seekers, covering claude.md, project overview, essential commands, required before running tests or cli (src/ layout) and run all tests (never skip - all must pass before commits).

yusufkaraaslan/Skill_Seekers · 5,387 tokens

octocode CLAUDE.md

Claude Code instructions for bgauryy/octocode: Read AGENTS.md. Discover repository skills under .agents/skills and activate only those matching the task.

bgauryy/octocode · 33 tokens

che-ical-mcp CLAUDE.md

Claude Code instructions for PsychQuant/che-ical-mcp, covering spectra instructions, use /spectra: skills when, workflow, parked changes and mcp 功能驗證的表面選擇（.claude/rules/mcp-binary-version-testing.md）.

PsychQuant/che-ical-mcp · 3,732 tokens

ai-workflow AGENTS.md

Instructions for cunhaax/ai-workflow, covering ai workflow template, rules — non-negotiable, project overview, commands and architecture.

cunhaax/ai-workflow · 2,602 tokens

substack-mcp-plus CLAUDE.md

Instructions for ty13r/substack-mcp-plus, covering claude.md, quick command reference (use these!), always activate virtual environment first, run tests (use python3!) and code quality.

ty13r/substack-mcp-plus · 2,882 tokens

dotsweep AGENTS.md

Instructions for stanmaygo/dotsweep, covering dotsweep-skill, this repo is a mirror, not the source, what must stay true and what is deliberately absent.

stanmaygo/dotsweep · 640 tokens