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/yogasw/wick/agents-mdgit clone --depth 1 https://github.com/yogasw/wickWhat 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 | $0.01887 | $0.01887 |
| Opus 5 | $0.00944 | $0.00944 |
| Sonnet 5 | $0.00377 | $0.00377 |
| Haiku 4.5 | $0.00189 | $0.00189 |
Grade A, and why
wick 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 2d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Operational rules for coding agents (Claude Code, etc.) working in this repo. Human onboarding lives in README.md.
Running the app (agent flow)
When an agent needs to start the server — e.g. to verify a UI change — use a one-shot flow, not watch mode:
- Make sure the Tailwind CLI is present (see below).
- Build CSS once:
- Windows:
./bin/tailwindcss.exe -i web/src/input.css -o web/public/css/app.css --minify - macOS/Linux:
./bin/tailwindcss -i web/src/input.css -o web/public/css/app.css --minify
- Windows:
- Run the server:
go run main.go server - Always kill the server when you're done. Don't leave background processes hanging.
Do NOT run make css/watch, make dev, or make run/live from an agent session — watchers are for interactive development, they don't terminate, and they waste the user's resources.
Tailwind CLI presence check
The standalone Tailwind binary is OS-specific and not committed. Before building CSS:
ls ./bin/tailwindcss* 2>/dev/null
If nothing is found, run make setup once — it auto-detects OS/arch and downloads the right binary to ./bin/.
Killing processes
- Anything you started (server, watcher, build job) must be killed before handing control back.
- If you encounter a process the user started (e.g. their own dev server already running on :9425), do NOT kill it silently. Ask first: "Looks like something is already running on :9425. OK to kill it, or are you using it?"
- Prefer
taskkill //F //PID <pid>on Windows (git bash),kill <pid>elsewhere.
Quick commands
| Task | Command |
|---|---|
| Build CSS once | ./bin/tailwindcss.exe -i web/src/input.css -o web/public/css/app.css --minify |
| Regenerate templ | templ generate |
| Compile check | go build ./... |
| Run server (foreground) | go run main.go server |
| Run tests | go test ./... |
| Setup Tailwind CLI | make setup (one-time) |
Before declaring a task done
templ generate && go build ./...passes.- Any process you started is stopped.
- Changes on the tool grid / Ctrl+K palette look right in both light and dark mode (if UI changed).
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.
- 2d ago First seen · 142 lines · 1,887 tokens per session scan A 9c4f5009f263
wick AGENTS.md is an instructions file published in the GitHub repository yogasw/wick (5 stars, last pushed 5d ago), licensed MIT. It adds 1,887 tokens to every session, about $0.0094 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
ai-workflow AGENTS.md
Instructions for cunhaax/ai-workflow, covering ai workflow template, rules — non-negotiable, project overview, commands and architecture.
trackly-cli CLAUDE.md
Claude Code instructions for trackly-app/trackly-cli, covering trackly-cli, tech stack, backend production source of truth, directory structure and key commands.
com-example-config-AsyncTestConfig
Instructions for PIsberg/vibetags, covering copilot instructions for asynctestconfig and immutable type.
pupila CLAUDE.md
Instructions for FranRom/pupila, covering claude.md, where things live, stack, run locally and repo layout.
claude-bridge AGENTS.md
Instructions for kadaba/claude-bridge, covering agents.md — using claude-bridge from any ai coding cli, two independent channels, 1. coordination (the conversation), 2. file transfer (the bytes) — same for every tool and workflows.
UsageAtlas AGENTS.md
Instructions for SRX9/UsageAtlas, covering repository guidelines and coding approach.