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/jellydn/zed-101-setup/agents-mdgit clone --depth 1 https://github.com/jellydn/zed-101-setupWrote 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/jellydn/zed-101-setup/agents-md)<a href="https://agentmods.dev/instructions/jellydn/zed-101-setup/agents-md"><img src="https://agentmods.dev/badge/instructions/jellydn/zed-101-setup/agents-md.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 | $0.00584 | $0.00584 |
| Opus 5 | $0.00292 | $0.00292 |
| Sonnet 5 | $0.00117 | $0.00117 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
zed-101-setup AGENTS.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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Repo overview
This repo is a Zed Editor configuration bundle — settings.json, keymap.json, tasks.json are the source files. README.md embeds them inside comment markers. cli.ts reads the source files and rewrites the README.
Developer commands
bun run lint # biome check .
bun run lint:fix # biome check --write .
bun run typecheck # tsc --noEmit
bun run start # bun run cli.ts (regenerates README.md)
bun run dev # bun run --hot cli.ts (hot-reload)
To install configs into your live Zed setup:
sh install.sh # backs up ~/.config/zed/, copies repo files there
README generation
cli.ts replaces <!-- ALL-SETTINGS:START/END -->, <!-- ALL-KEYMAPS:START/END -->, and <!-- ALL-TASKS:START/END --> markers in README.md with the current content of settings.json, keymap.json, and tasks.json. After writing, it runs prettier --write on README.md (falls back to npx prettier, warns if neither is available).
To regenerate from your live Zed config:
sh cli.sh # copies from ~/.config/zed/, then runs bun run start
Do not manually edit README sections between the comment markers — they are overwritten by cli.ts. Edit settings.json, keymap.json, or tasks.json directly instead.
JSONC caveat
settings.json and keymap.json are JSONC (JSON with Comments), not valid JSON. Biome handles them (json.parser.allowComments: true), but standard JSON linters will choke. They are listed in .gitignore for this reason, yet still tracked in git — don't be confused by the gitignore entry.
Pre-commit & CI
- Prettier handles
html,css,markdownfiles. - Biome handles everything else (format, imports, lint, safe fixes).
- CI (
.github/workflows/pre-commit.yml) runs pre-commit on PRs and pushes tomain, then auto-commits any formatting fixes viastefanzweifel/git-auto-commit-action@v7.
Style notes
- TypeScript: strict mode,
verbatimModuleSyntax,noEmit, ESNext target/module. - Bun runtime — lockfile is
bun.lockb. - Biome is the linter/formatter; ESLint is only in
example/. - Renovate automerges non-major deps and pins all except peer dependencies.
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 · 51 lines · 584 tokens per session scan A a60e32ff9431
zed-101-setup AGENTS.md is an instructions file published in the GitHub repository jellydn/zed-101-setup (1,441 stars, last pushed yesterday), licensed MIT. It adds 584 tokens to every session, about $0.0029 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
awesome-copilot copilot-instructions.md
Copilot instructions for github/awesome-copilot, covering readme updates, prompt file guide, instruction file guide, agent file guide and agent skills guide.
maui uitests.instructions.md
Instructions for dotnet/maui, covering ui testing guidelines for .net maui, ui test structure, two-project requirement, base class and infrastructure and naming conventions.
maui helix-device-tests.instructions.md
Guidelines for running and configuring .NET MAUI device tests on Helix infrastructure.
maui ci-copilot-pipeline-security.instructions.md
Security rules for the Copilot PR-review pipeline. Read before editing.
maui xaml-unittests.instructions.md
Guidelines for writing XAML unit tests in the Controls.Xaml.UnitTests project.
awesome-ai-apps AGENTS.md
Instructions for Arindam200/awesome-ai-apps, covering agents.md, repository overview, project categories, common development commands and running individual projects.