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/chemaclass/agnostic-ai/copilot-instructionsgit clone --depth 1 https://github.com/Chemaclass/agnostic-aiWrote 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/chemaclass/agnostic-ai/copilot-instructions)<a href="https://agentmods.dev/instructions/chemaclass/agnostic-ai/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/chemaclass/agnostic-ai/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 5.1 | $0.00453 | $0.00453 |
| Opus 5 | $0.00227 | $0.00227 |
| Sonnet 5 | $0.00091 | $0.00091 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
agnostic-ai 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 5d 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.
What it actually says
AI Project Conventions
This file is regenerated by agnostic-ai. Every supported AI tool reads a copy of this body from its native entry-point (CLAUDE.md, AGENTS.md, GEMINI.md, CONVENTIONS.md, ...) so a single source of truth drives every target.
Where the specs live
- Agents:
.agnostic-ai/agents/ - Skills:
.agnostic-ai/skills/ - Rules:
.agnostic-ai/rules/(one file per rule) - Hooks:
.agnostic-ai/hooks/(rendered into the target-native location) - MCP servers:
.agnostic-ai/mcps/ - Commands:
.agnostic-ai/commands/ - Settings:
.agnostic-ai/settings/(permissions, model; Claude only today) - Reviews:
.agnostic-ai/reviews/(code-review bot guidance; Cursor BUGBOT.md today) - Environments:
.agnostic-ai/environments/(dev-env bootstrap; Cursor environment.json today) - Ignore:
.agnostic-ai/ignore/(agent ignore patterns; .cursorignore, .aiexclude, .aiderignore)
Target-specific overlays
Per-target configuration that does not fit the agnostic spec kinds above lives under .agnostic-ai/overlays/. The Claude adapter, for example, captures the non-hooks portion of .claude/settings.json (statusLine, enabledPlugins, ...) into .agnostic-ai/overlays/claude.settings.json on import claude. sync reads that overlay and layers the spec-derived hooks key on top.
Workflow
- Author specs under the directories above.
- Run
agnostic-ai syncto regenerate per-target output files. - Edit only the source specs; the per-target files (including this one) are overwritten on each sync.
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.
- 5d ago First seen · 29 lines · 453 tokens per session scan A cd4ea28accd2
agnostic-ai copilot-instructions.md is an instructions file published in the GitHub repository Chemaclass/agnostic-ai (11 stars, last pushed today), licensed MIT. It adds 453 tokens to every session, about $0.0023 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
codedb AGENTS.md
AGENTS.md instructions for justrach/codedb, covering codedb agent guidelines, what codedb is (and isn't), review guidelines, pre-merge verification and security-sensitive areas.
codedb copilot-instructions.md
Copilot instructions for justrach/codedb, covering codedb — agent instructions, project, rules, filing issues and test style.
codedb CLAUDE.md
Claude Code instructions for justrach/codedb, covering codedb — agent instructions, project, rules, filing issues and test style.
TLDR CLAUDE.md
Instructions for 0p9b/TLDR, covering claude.md — tldr maintainer guide, product, source layout, edit rules and install paths.
TLDR AGENTS.md
Instructions for 0p9b/TLDR: @./skills/tldr/SKILL.md @./skills/tldr-commit/SKILL.md @./skills/tldr-review/SKILL.md @./skills/tldr-compress/SKILL.md.
agman CLAUDE.md
Instructions for memandip/agman, covering claude.md — agman, what this project is, architecture — what you're editing, hard constraints (do not break these) and branch & pr workflow (required).