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/branover/hexgraph/claude-mdgit clone --depth 1 https://github.com/branover/hexgraphWhat 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 | $0.10745 | $0.10745 |
| Opus 5 | $0.05372 | $0.05372 |
| Sonnet 5 | $0.02149 | $0.02149 |
| Haiku 4.5 | $0.01074 | $0.01074 |
Grade C, and why
hexgraph CLAUDE.md scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- The task runner is **`just`** (install: `curl --proto '=https' --tlsv1.2 -sSf https://just.systems/install.sh | bash -s -- --to ~/.local/bin`, or `snap install just`; `~/.local/bin` on `PATH`). Bare **`just`** prints t Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- The task runner is **`just`** (install: `curl --proto '=https' --tlsv1.2 -sSf https://just.systems/install.sh | bash -s -- --to ~/.local/bin`, or `snap install just`; `~/.local/bin` on `PATH`). Bare **`just`** prints t The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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 · 221 lines · 10,745 tokens per session scan C 3fe00c58d5a0
hexgraph CLAUDE.md is an instructions file published in the GitHub repository branover/hexgraph (19 stars, last pushed 17d ago), licensed AGPL-3.0. It adds 10,745 tokens to every session, about $0.0537 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
crystal CLAUDE.md
Instructions for stravu/crystal, covering crystal - multi-session claude code manager, project overview, references, implementation status: ✅ complete and ✅ implemented features.
agent-ship CLAUDE.md
Instructions for Agent-Ship/agent-ship, covering claude.md, project overview, commands, docker development (recommended) and local development (no docker).
clawock AGENTS.md
Instructions for KCNyu/clawock, covering agents.md - your workspace, every session, kcn 偏好, git hook (one-time setup per clone) and git auto-commit rules.
agents CLAUDE.md
Instructions for eloylp/agents, covering claude.md, project overview, directory structure, config model and build & run.