Borrowing it
Nothing to install: this file belongs to JosephOIbrahim/Hanna. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JosephOIbrahim/Hanna/main/CLAUDE.mdgit clone --depth 1 https://github.com/JosephOIbrahim/HannaWrote 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/josephoibrahim/hanna/claude-md)<a href="https://agentmods.dev/instructions/josephoibrahim/hanna/claude-md"><img src="https://agentmods.dev/badge/instructions/josephoibrahim/hanna/claude-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 5.1 | $0.00699 | $0.00699 |
| Opus 5 | $0.00349 | $0.00349 |
| Sonnet 5 | $0.00140 | $0.00140 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
Hanna CLAUDE.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 8d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hanna — Claude Code Project Instructions
Project-local instructions. Supplements (does not replace) the global instructions at ~/.claude/CLAUDE.md. Where this file and the global conflict, this file wins for work inside /Users/rustybeard/Code/Hanna.
What Hanna is
An always-on AI producer cloned from Harlo's substrate. Surfaces decisions; does not make them. See HANNA_BLUEPRINT.md for the architectural spec.
Hanna inherits the 33 inviolable rules from Harlo plus 4 producer-specific addenda. See RULES.md.
Hanna conventions accrete as sessions resolve open questions. See docs/CONVENTIONS.md.
Read edges
- Harlo: read-only via
src/harlo_bridge.py. Hanna never writes to Harlo. (Rule 35.) - Octavius: request-only via
src/octavius_bridge.py. Spawn / poll / harvest only. (Rule 35.)
Commit trailer (canonical)
Every commit in this repo ends with the canonical Claude Code format:
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <[email protected]>
If model-version analytics are needed, add a separate trailer line adjacent to (not inside) Co-Authored-By:
Model-Version: claude-opus-4-7-1m
The Co-Authored-By slot is reserved for the canonical Claude <[email protected]> to avoid impersonation-classifier false positives. Any other form (e.g. Claude Opus 4.7 (1M context)) trips the auto-mode classifier and is disallowed.
This rule is duplicated in ~/.claude/CLAUDE.md for global enforcement. Both files agree.
Patent topics
Rule 37. Never raised. No exceptions in any session, commit message, or doc generated under this repo.
Family-first lockout
Rule 34. Sessions outside Mon–Fri 09:00–17:00 ET pause by default. Override path is explicit — a single yes from Joe per session — and is logged in the session prompt.
Sessions
Sessions are numbered. Each session ships its own deliverable on a feature branch:
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.
- 8d ago First seen · 78 lines · 699 tokens per session scan A 8f1439bacd48
Hanna CLAUDE.md is an instructions file published in the GitHub repository JosephOIbrahim/Hanna (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 699 tokens to every session, about $0.0035 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.