Borrowing it
Nothing to install: this file belongs to honzapav/portuni. 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/honzapav/portuni/main/CLAUDE.mdgit clone --depth 1 https://github.com/honzapav/portuniWrote 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/honzapav/portuni/claude-md)<a href="https://agentmods.dev/instructions/honzapav/portuni/claude-md"><img src="https://agentmods.dev/badge/instructions/honzapav/portuni/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/honzapav/portuni/claude-md"><img src="https://agentmods.dev/badge/instructions/honzapav/portuni/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.13487 | $0.13487 |
| Opus 5 | $0.06744 | $0.06744 |
| Sonnet 5 | $0.02697 | $0.02697 |
| Haiku 4.5 | $0.01349 | $0.01349 |
Grade B, and why
portuni CLAUDE.md scanned grade B with 1 finding 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 3d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`~/.claude.json` (`install_claude_global`), `~/.codex/config.toml` How it starts
The opening of the file, as written. The whole thing — 779 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Portuni – Claude guide
Knowledge graph for organisations (POPP: organisations, projects, processes, areas, principles). Backend Node + libSQL (Turso), frontend React + Vite, desktop shell Tauri 2.
Daily dev workflow
Run backend and frontend separately. Stay out of Tauri unless shipping a new
.app or touching desktop-specific code. The installed
/Applications/Portuni.app is the daily driver for actual data work; update
it on release checkpoints, not per commit.
Backend (tmux portuni-mcp, port 4011)
The standalone HTTP/MCP server – what Claude Code in mirror dirs talks to.
npm run build # tsc -> dist/, ~2 s
tmux send-keys -t portuni-mcp C-c Up Enter # restart server
Started once: tmux new -d -s portuni-mcp 'varlock run -- node dist/index.js 2>&1 | tee /tmp/portuni-mcp.log'.
Logs at /tmp/portuni-mcp.log and in the tmux pane.
Frontend (Vite, port 4010)
varlock run -- npm --prefix apps/web run dev
Open http://portuni.test (localias) or http://localhost:4010. Save a
.tsx, HMR pushes the change. Vite proxies /api/* to 4011 and injects the
auth token from env (hence varlock).
Desktop (Tauri) – rare
Only when shipping a new Portuni.app or testing desktop-specific wiring
(sidecar boot, per-launch auth token, env passing, Tauri commands).
Always build the installable .app signed — never adhoc/bare
cargo tauri build. An adhoc build reads to macOS as a different
app (identity = binary hash), so every reinstall re-triggers the whole
Keychain "Always Allow" gauntlet and breaks Gatekeeper trust. Use the
wrapper, which signs with the Developer ID (identity stable across
rebuilds → Keychain grants persist) and verifies the bundle:
# local reinstall (signed, not notarized — Gatekeeper only checks
# downloaded apps, so notarization is unnecessary for your own machine)
APPLE_SIGNING_IDENTITY='Developer ID Application: JAN PÁV (98H25UC996)' \
scripts/build-signed.sh --no-notarize
cp -R apps/desktop/target/release/bundle/macos/Portuni.app /Applications/
# distribution build (adds notarization + staples the DMG) — full run:
# scripts/build-signed.sh (needs APPLE_ID/APPLE_PASSWORD/APPLE_TEAM_ID,
# or the Keychain profile `portuni-notary`; secrets in Bitwarden
# "Portuni Apple signing"). See docs/release-process.md.
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.
- 3d ago Changed · +499 lines · +8,901 tokens per session b5a25dcaca96
- 8d ago First seen · 280 lines · 4,586 tokens per session scan B 63768aac2cee
portuni CLAUDE.md is an instructions file published in the GitHub repository honzapav/portuni (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 13,487 tokens to every session, about $0.0674 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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.