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/eliransu/digital-brain/copilot-instructionsgit clone --depth 1 https://github.com/eliransu/digital-brainWrote 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/eliransu/digital-brain/copilot-instructions)<a href="https://agentmods.dev/instructions/eliransu/digital-brain/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/eliransu/digital-brain/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 | $0.00711 | $0.00711 |
| Opus 5 | $0.00356 | $0.00356 |
| Sonnet 5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
digital-brain 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 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.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
digital-brain: GitHub Copilot Instructions
This repository is a Claude Code plugin and Obsidian vault that builds persistent, compounding knowledge bases using Andrej Karpathy's LLM Wiki pattern. It is markdown-only. No build step, no compiled code, no runtime dependencies.
Project Type
- Agent Skills package (cross-platform Agent Skills standard)
- Obsidian vault (interpretable by Obsidian directly)
- Claude Code plugin (installable via marketplace)
Repository Layout
skills/: 10 skills, each with aSKILL.mddefining trigger phrases and instructionshooks/hooks.json: Claude Code lifecycle hooks (SessionStart, PostCompact, PostToolUse, Stop).claude-plugin/plugin.json: plugin manifestwiki/: generated knowledge base (Markdown files with YAML frontmatter).raw/: immutable source documents (never modify)_templates/: Obsidian Templater templates_attachments/: images and PDFs referenced by wiki pages
Conventions Copilot Should Follow
When suggesting edits:
- Frontmatter is flat YAML with plural keys:
tags,aliases,cssclasses - Internal links are wikilinks:
[[Note Name]], not Markdown links to.mdpaths - Dates are
YYYY-MM-DD, not ISO datetimes .raw/is immutable. Never suggest edits to anything under that pathwiki/log.mdis append-only, with new entries at the topwiki/hot.mdis overwritten at session end, not appended to- Skills use only
nameanddescriptionin frontmatter. Noallowed-tools, notriggers, noglobs(these are not part of the Agent Skills spec) - Custom callouts: this vault defines
[!contradiction],[!gap],[!key-insight],[!stale]in.obsidian/snippets/vault-colors.css. These render only with that snippet enabled.
When Editing Skills (skills/<name>/SKILL.md)
- Frontmatter:
name(matches directory name) anddescription(single quoted line, max ~250 useful chars) - Body: short, imperative instructions. Reference files with backticks. Do not paste large code blocks unless they're essential.
- Trigger phrases go in the
descriptionfield, not in body or non-standard fields
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.
- 3d ago First seen · 51 lines · 711 tokens per session scan A 7dca08c1aff0
digital-brain copilot-instructions.md is an instructions file published in the GitHub repository eliransu/digital-brain (1 stars, last pushed 3mo ago), licensed MIT. It adds 711 tokens to every session, about $0.0036 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.
Other instructions, from other repositories
llm-wiki-plugin AGENTS.md
AGENTS.md instructions for praneybehl/llm-wiki-plugin, covering repository instructions and releases.
zissa-wiki CLAUDE.md
Instructions for MetamusicX/zissa-wiki, covering claude.md — research wiki schema, identity, architecture, folder conventions and raw/.
student-llm-wiki AGENTS.md
Instructions for IssacW228/student-llm-wiki, covering student llm wiki — agent instructions, 操作规则 operation rules, token预算规则（最高优先级）, 架构 architecture and 命令 commands.
marketing-machine CLAUDE.md
Instructions for cagatayuncu/marketing-machine, covering marketing-machine — contributor notes, commands, architecture in ten lines and invariants (violating these is a bug, not a style choice).
obsidian-mcp-rs CLAUDE.md
Instructions for MrRefactoring/obsidian-mcp-rs, covering claude.md, commands, build / run, tests and lint gates enforced by ci (.github/workflows/ci.yml).
ship AGENTS.md
Instructions for heliohq/ship, covering agents.md, commands, repository map, architecture and code style.