Borrowing it
Nothing to install: this file belongs to edible999999999-jpg/humhum. 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/edible999999999-jpg/humhum/main/AGENTS.mdgit clone --depth 1 https://github.com/edible999999999-jpg/humhumWrote 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/edible999999999-jpg/humhum/agents-md)<a href="https://agentmods.dev/instructions/edible999999999-jpg/humhum/agents-md"><img src="https://agentmods.dev/badge/instructions/edible999999999-jpg/humhum/agents-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/edible999999999-jpg/humhum/agents-md"><img src="https://agentmods.dev/badge/instructions/edible999999999-jpg/humhum/agents-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 | $0.01948 | $0.01948 |
| Opus 5 | $0.00974 | $0.00974 |
| Sonnet 5 | $0.00390 | $0.00390 |
| Haiku 4.5 | $0.00195 | $0.00195 |
Grade A, and why
humhum AGENTS.md scanned grade A 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
When the user says a session should be "重点监控", "加入 Hexa", "让 Hexa 看着这轮", "watch this session", or similar, the current agent should bind itself to Hexa without asking the user to copy curl commands. How it starts
The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file guides AI coding agents working on HUMHUM.
Product Position
HUMHUM is a personal Agent hub for the Agent era.
It is not another dashboard, not another generic assistant, and not a tool that asks users to manage every config file themselves. HUMHUM quietly reads local user-owned context, agent files, sessions, skills, memories, rules, app signals, and project traces, then turns that evidence into usable personal knowledge.
The product promise is simple:
Let every Agent work around the user, while the user stays calm and in control.
Core Principle
HUMHUM may collect and index technical evidence in the background, but the foreground experience must explain what it means for the user.
Do not expose raw internals by default:
- Do not lead with asset counts, file paths, roots, JSON, YAML, or tool tables.
- Do not make users read scan diagnostics unless they explicitly open details.
- Do not treat "found many files" as product value.
Do expose interpreted personal knowledge:
- What kind of work the user seems to be doing.
- Which skills and workflows they rely on.
- Which preferences should become durable memory.
- Which repeated mistakes, risks, or unfinished loops need gentle attention.
- What the next small useful action should be.
Product Roles
Humi
Humi is the warm personal interpreter.
It quietly learns from the user's local agent activity and answers in plain language. Humi should feel like a calm companion who understands the user's rhythm, not a terminal report. Its default surface is a conversation box, not a form.
Humi may use:
~/.humhum/knowledge.json~/.humhum/stats.json~/.humhum/local-agent-memory.md- scanned Codex, Claude, Qoder, Pi, and project assets
- local session summaries and tool usage
Humi should translate those signals into:
- user profile
- working direction
- common skills
- preferences
- memory suggestions
- soft next steps
Hype
Hype manages the user's personal Agent knowledge base.
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.
- 12d ago First seen · 201 lines · 1,948 tokens per session scan A fc763ae76295
humhum AGENTS.md is an instructions file published in the GitHub repository edible999999999-jpg/humhum (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,948 tokens to every session, about $0.0097 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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.
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).
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).