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/nimblebraininc/upjack/claude-mdgit clone --depth 1 https://github.com/NimbleBrainInc/upjackWrote 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/nimblebraininc/upjack/claude-md)<a href="https://agentmods.dev/instructions/nimblebraininc/upjack/claude-md"><img src="https://agentmods.dev/badge/instructions/nimblebraininc/upjack/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 | $0.02010 | $0.02010 |
| Opus 5 | $0.01005 | $0.01005 |
| Sonnet 5 | $0.00402 | $0.00402 |
| Haiku 4.5 | $0.00201 | $0.00201 |
Grade A, and why
upjack 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 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.
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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NimbleBrain Upjack Framework
Declarative AI-native application framework. Apps are MCPB packages with a _meta["ai.nimblebrain/upjack"] extension.
Current version: 0.1.0
Package names: upjack on PyPI, upjack on npm
Directory Layout
lib/python/ Python library (upjack) — source in src/upjack/
lib/typescript/ TypeScript library (upjack) — source in src/
schemas/ JSON Schemas (upjack-entity, upjack-manifest) + validation tooling
skills/ Publishable skills (upjack-app-builder) — symlinked from .claude/skills/
examples/ Reference apps (CRM, Todo, Research Assistant)
website/ Documentation site (Astro/Starlight) — upjack.dev
workspace/ Runtime entity data (gitignored, created at runtime)
Key Modules (Python)
| Module | Purpose |
|---|---|
upjack.relations |
Write-time reverse relationship index — query_reverse(), rebuild_index() |
upjack.activity |
Activity entity tracking — log_activity(), get_activities() |
Graph Traversal (UpjackApp)
Methods for navigating entity relationships:
query_by_relationship(entity_type, rel, target_id, filter?, limit?)— reverse index lookup (e.g., find all deals linked to a contact)get_related(entity_id, rel?, direction?)— follow edges forward or reverse, returns resolved entitiesget_composite(entity_type, entity_id, depth?)— load entity + all related in one call;_relatedkey contains forward (rel) and reverse (~rel) edges
CRUD hooks: on_relationships_changed callback fires on create_entity, update_entity, delete_entity — UpjackApp auto-wires this to maintain the reverse index.
Activity Tracking
Opt-in via "activities": true in manifest _meta["ai.nimblebrain/upjack"] extension.
log_activity(subject_id, action, detail?)— creates an activity entity with a subject relationshipget_activities(subject_id, action?, limit?)— reverse index query for a subject's activities- Activity schema:
action(string, required),detail(object, optional)
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 First seen · 179 lines · 2,010 tokens per session scan A b6c2b027f946
upjack CLAUDE.md is an instructions file published in the GitHub repository NimbleBrainInc/upjack (9 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 2,010 tokens to every session, about $0.0100 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
jesse AGENTS.md
AGENTS.md instructions for jesse-ai/jesse, covering jesse repository guide for ai agents, skills, key characteristics, central framework and technology stack.
laravel AGENTS.md
AGENTS.md instructions for laravel/laravel, covering laravel application, prerequisites and agent setup.
AgentEval copilot-instructions.md
Instructions for AgentEvalHQ/AgentEval, covering agenteval - ai coding agent instructions, architecture overview, environment setup, optional: secondary models for comparison and build & test commands.
LarAgent AGENTS.md
Instructions for MaestroError/LarAgent, covering purpose, key principles, planning, executing plan and testing.
zhin zhin-plugin.instructions.md
Instructions for zhinjs/zhin, covering zhin plugin runtime authoring, package contract, convention directories, imports and native typescript and command routes.
igniter-js GEMINI.md
Gemini CLI instructions for felipebarcelospro/igniter-js, covering 1. identity and profile, 2. about the igniter.js monorepo, 3. personality and communication, 4. lia's core responsibilities (the 4 pillars) and 5. technical guidelines and methodology.