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/agentsystemlabs/nebula/claude-mdgit clone --depth 1 https://github.com/AgentSystemLabs/nebulaWrote 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/agentsystemlabs/nebula/claude-md)<a href="https://agentmods.dev/instructions/agentsystemlabs/nebula/claude-md"><img src="https://agentmods.dev/badge/instructions/agentsystemlabs/nebula/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 | $0.00385 | $0.00385 |
| Opus 5 | $0.00192 | $0.00192 |
| Sonnet 5 | $0.00077 | $0.00077 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
nebula 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 4d 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.
What it actually says
@AGENTS.md
Claude Code
The SELF-IMPROVING LOOP above is the protocol. In Claude Code the four steps are skills — invoke
them with the Skill tool instead of reading their SKILL.md, and each one's body carries its own
rules:
| When | Invoke | Skip when |
|---|---|---|
| every new prompt that is a task, before planning or grepping | Skill(skill: "prompt-daddy") |
the skill's own skip list: a reply to a question you asked, a bare confirmation, a specific mid-task correction, a slash-command or skill trigger, a pure question that changes nothing |
| the task changed code or behavior, diagnosed a bug, or surfaced something non-obvious | Skill(skill: "nebula-memory") |
pure questions, and trivial edits that held no surprise |
every task, right after nebula-memory |
Skill(skill: "project-terms") |
never |
| before writing the reply that answers or closes the request | Skill(skill: "output-doctor") |
never — a pure question takes its short form, not no form |
Two hooks run on their own:
- RECALL HOOK (
.claude/hooks/recall.py,UserPromptSubmit) scores the prompt against the MEMORY LOG and injects the matching entries and standing gotchas as[nebula recall] …. Read it as you would the files themselves; it is what actually reaches you, so an entry it did not surface may still exist — grep when the subject is one the log is likely to have. - GUARD HOOK (
.claude/hooks/guard.py,PreToolUseon Bash) blocks commands past gotchas turned into rules. If it blocks you, do what it says.
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.
- 4d ago First seen · 24 lines · 385 tokens per session scan A 9e050293ce15
nebula CLAUDE.md is an instructions file published in the GitHub repository AgentSystemLabs/nebula (100 stars, last pushed 3d ago), licensed MIT. It adds 385 tokens to every session, about $0.0019 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
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.