What is access-to copilot-instructions.md?

A repository-specific instruction file for GitHub Copilot, an AI coding assistant, in the Access To project.

It is for working consistently with the project's static site, admin system, configuration files, scripts, workflows, and child repositories.

It gives the assistant the project's architecture, file locations, and coding conventions so its changes fit the repository.

How dougdevitre/access-to configures GitHub Copilot

Reuse

Borrowing it

Nothing to install: this file belongs to dougdevitre/access-to. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/dougdevitre/access-to/main/.github/copilot-instructions.md

Clone the repo

git clone --depth 1 https://github.com/dougdevitre/access-to

Made for: GitHub Copilot.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/dougdevitre/access-to/copilot-instructions/github.svg)](https://agentmods.dev/instructions/dougdevitre/access-to/copilot-instructions)

Your own site

<a href="https://agentmods.dev/instructions/dougdevitre/access-to/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/dougdevitre/access-to/copilot-instructions/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/dougdevitre/access-to/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/dougdevitre/access-to/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 692 This file is loaded in full into every session.

When invoked 692 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00692	$0.00692
Opus 5.5	$0.00277	$0.00277
Sonnet 5.5	$0.00138	$0.00138
Haiku 4.5	$0.00069	$0.00069

Measured 2mo ago against content hash edc5c4cfe79d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

access-to copilot-instructions.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 2mo 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.

.github/copilot-instructions.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Instructions for Access To

You are working in the Access To ecosystem — a collection of open-source Claude Skills that close access gaps in housing, jobs, health, education, services, safety, and business.

Architecture

This is the hub repository. It contains:

A static landing site (HTML/CSS, no frameworks)
An admin system that manages 8 interconnected repos
Config-driven automation (.github/config/, .github/scripts/, .github/workflows/)

Child repos each contain a SKILL.md file — a structured prompt system designed to run inside Claude.ai Projects with no code.

Key conventions

File structure

Config files live in .github/config/ (JSON, validated by schemas in .github/schemas/)
Admin scripts live in .github/scripts/ (bash, all source lib-log.sh for structured logging)
Workflows live in .github/workflows/ (thin orchestration that calls scripts)
Static site files are in the repo root (HTML, CSS, no build step)

Code style

HTML: Semantic elements, ARIA labels, no inline styles
CSS: Use existing CSS variables defined in styles.css. No frameworks.
JavaScript: Vanilla JS only. No frameworks, no npm, no dependencies.
Bash scripts: Use set -euo pipefail. Source lib-log.sh. Use log_info, log_warn, log_error, log_action instead of raw echo.
JSON configs: Follow the schemas in .github/schemas/. Run validate-config.sh after changes.

Cross-repo awareness

The repo registry is .github/config/repos.json — always check it for repo names, pillars, and connections.
Labels are defined in .github/config/labels.json — use the namespace:value convention (e.g., pillar:housing, type:bug, status:triage).
When a change affects multiple repos, use the cross-repo label and reference the hub coordination issue.

What NOT to do

Do not add npm, bundlers, or build tools to the hub site
Do not hardcode repo lists — read from repos.json
Do not use echo for logging in scripts — use lib-log.sh functions
Do not suppress errors with 2>/dev/null without capturing the output first
Do not add inline styles to HTML — use CSS variables

Read the full file on GitHub · 54 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.

2mo ago First seen · 54 lines · 692 tokens per session scan A edc5c4cfe79d

Subscribe to this mod's changes

access-to copilot-instructions.md is an instructions file published in the GitHub repository dougdevitre/access-to (1 stars, last pushed 13d ago), licensed MIT. It adds 692 tokens to every session, about $0.0028 per session on Opus 5.5. 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-justice ai-tools anthropic civic-tech claude-ai claude-skill

access-to copilot-instructions.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
access-to copilot-instructions.mddougdevitre/access-to	Instructions file	1	13d ago	MIT	A	692	GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

access-to: Instructions file for GitHub Copilot