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 instructions/canonical/copilot-collections/copilot-instructionsgit clone --depth 1 https://github.com/canonical/copilot-collectionsWrote 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/instructions/canonical/copilot-collections/copilot-instructions)<a href="https://agentmods.dev/instructions/canonical/copilot-collections/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/canonical/copilot-collections/copilot-instructions.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 | $0.01215 | $0.01215 |
| Opus 5 | $0.00607 | $0.00607 |
| Sonnet 5 | $0.00243 | $0.00243 |
| Haiku 4.5 | $0.00121 | $0.00121 |
Grade A, and why
copilot-collections 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 4d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions for canonical/copilot-collections
This repository is the "Toolkit" for centralized context management for GitHub Copilot across the Canonical ecosystem. It distributes standardized Copilot Custom Instructions and Prompts to other repositories via a subscription model.
High Level Details
- Type: Utility/Toolkit.
- Languages: Bash (logic), YAML (configuration), Markdown (content).
- Core Function: Individual repositories define a
.copilot-collections.yamlfile listing "Collections" they need. This toolkit's scripts (install_collections.sh) parse that config and sync the corresponding Markdown files fromassets/orgroups/<team>/into the consumer's.github/directory. - Supported Artifacts: Custom Instructions, Prompts, and Agent Skills.
- Key Tools:
yq(YAML processing),shellcheck(Script linting).
Project Layout
Directories
collections.yaml: The ROOT configuration file defining "Core" collections.assets/: Contains source Markdown files for core instructions, prompts, and agents.instructions/: Custom instruction files organized by category.prompts/: Prompt template files.agents/: Agent definition files.
skills/: Contains core agent skill directories (each containing SKILL.md with YAML frontmatter).groups/: Contains team-specific collections.- Each subfolder (e.g.,
groups/charm-tech/) acts as a mini-repo with its owncollections.yamland asset folder.
- Each subfolder (e.g.,
scripts/: Contains the logic binaries.install_collections.sh: The main engine that reads config and copies files.validate_collections.sh: Validates referential integrity ofcollections.yamlfiles.local_sync.sh: A wrapper for local usage by consumers.
tests/: Contains test scripts for the bash logic..github/workflows/:test-toolkit.yaml: The CI pipeline for this repo.auto_update_collections.yaml: A reusable workflow imported by consumer repos to auto-update their instructions.
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.
- 4d ago First seen · 121 lines · 1,215 tokens per session scan A fd4e75a66935
copilot-collections copilot-instructions.md is an instructions file published in the GitHub repository canonical/copilot-collections (29 stars, last pushed 6d ago), licensed Apache-2.0. It adds 1,215 tokens to every session, about $0.0061 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.
Other instructions, from other repositories
ai-platform-engineering AGENTS.md
AGENTS.md instructions for caipe-io/ai-platform-engineering, covering agent instructions, project structure, find the canonical implementation, documentation and docs & spec rules.
kubara AGENTS.md
AGENTS.md instructions for kubara-io/kubara, covering ai agent context, scope, product intent (stable), truth hierarchy and reference map.
neat CLAUDE.md
Claude Code instructions for neat-technologies/neat, covering claude.md, binding rules, what neat is, what success looks like and conventions.
axum-harness AGENTS.md
Instructions for openclosed-org/axum-harness, covering agents.md, 1. language, 2. repository identity, 3. operating posture and 4. development loop.
kubara CLAUDE.md
Claude Code instructions for kubara-io/kubara, a project described as: kubara is a single binary CLI tool written in Go providing a lightweight framework for bootstrapping Kubernetes platforms with production-proven best practices.
ai-platform-engineering CLAUDE.md
Claude Code instructions for caipe-io/ai-platform-engineering, a project described as: CAIPE is an open-source AI platform for building, deploying, governing, and operating AI agents and agentic workflows for platform engineering and beyond.