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/posthog/wizard/agents-mdgit clone --depth 1 https://github.com/PostHog/wizardWhat 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 | $0.02353 | $0.02353 |
| Opus 5 | $0.01177 | $0.01177 |
| Sonnet 5 | $0.00471 | $0.00471 |
| Haiku 4.5 | $0.00235 | $0.00235 |
Grade A, and why
wizard 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — PostHog Wizard
Instructions for all agents (and humans) working in this repo. This is the
single source of truth; CLAUDE.md just points here. User-facing
docs: https://posthog.com/docs/ai-engineering/ai-wizard
The PostHog wizard (npx @posthog/wizard) is a CLI that adds PostHog to a user's project using an AI agent. It authenticates the user, detects their framework, runs an agent that integrates the SDK and instruments events, and walks the user through their first dashboard. All from the terminal.
Design discipline
This codebase follows a specific design discipline: product knowledge never enters infrastructure code. The runner pipeline, the TUI store, the detection loop, and the prompt assembler are machinery. They don't know what PostHog is. They don't know what a framework is. They execute a pipeline driven by typed configuration surfaces.
Each domain has a dedicated boundary:
- Frameworks →
FrameworkConfiginsrc/frameworks/<name>/ - Integration knowledge → markdown skills in the context-mill repo
- Security policy → YARA-X rules in the warlock sibling repo. The wizard wires the scanner via PostToolUse/PreToolUse hooks (
src/lib/yara-hooks.ts); the rule content itself lives in warlock. To disable scanning in the field without a release, see the kill-switch runbook:docs/runbooks/warlock-kill-switch.md. ONLY USE THIS IF ABSOLUTELY NECESSARY. - Programs → step arrays in
src/lib/programs/ - TUI → screen components and primitives in
src/ui/tui/
Adding a new concern means finding the narrowest existing surface, not adding logic to the runner. The wizard is small (~20K lines) because boundaries prevent damage from propagating between concerns.
Before making structural changes
Read .claude/skills/wizard-development/SKILL.md first. It covers the design discipline, a decision framework for new extensions, and warning signs that a change is drifting off-pattern. Two reference files extend it:
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 · 170 lines · 2,353 tokens per session scan A 31101ad0e0b8
wizard AGENTS.md is an instructions file published in the GitHub repository PostHog/wizard (190 stars, last pushed 2d ago), licensed MIT. It adds 2,353 tokens to every session, about $0.0118 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
claude-for-designers CLAUDE.md
Instructions for mshadmanrahman/claude-for-designers, covering claude for designers: how to work in this folder, what this folder is, when the student asks about the folder, orient them, work out which class they are on before you answer and answer keys: never open one unasked.
posthog.com AGENTS.md
AGENTS.md instructions for PostHog/posthog.com, covering agents.md, making changes, prs, content prs and before you open a pr.
posthog.com CLAUDE.md
Claude Code instructions for PostHog/posthog.com, a project described as: Official docs, website, and handbook for PostHog.
solana-uiux-onboarding-kit CLAUDE.md
Instructions for draaujpeg/solana-uiux-onboarding-kit, covering solana ui/ux onboarding kit, language, where the truth lives, commands and always.
mcp CLAUDE.md
Instructions for PostHog/mcp, covering claude.md, development commands, code architecture, project structure and key components (typescript implementation).
survey-mcp-server AGENTS.md
Instructions for cyanheads/survey-mcp-server, covering agent protocol & architectural mandate, i. core principles (non‑negotiable), ii. architectural overview & directory structure, iii. architectural philosophy: pragmatic solid and iv. tool development workflow.