What is product-help?

A documentation-based help assistant for octo, a product with commands, skills, workflows, browser tools, and configuration.

Use it to learn how octo works, find the right documentation, or diagnose problems with commands, settings, skills, workflows, and connections.

It answers usage questions and investigates errors by checking the product documentation instead of guessing about features.

product-help — Skill for Claude Code and Codex by open-octo

Install

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.

Any agent

npx skills add open-octo/octo-agent --skill product-help

Clone the repo

git clone --depth 1 https://github.com/open-octo/octo-agent

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/open-octo/octo-agent/product-help/github.svg)](https://agentmods.dev/skills/open-octo/octo-agent/product-help)

Your own site

<a href="https://agentmods.dev/skills/open-octo/octo-agent/product-help"><img src="https://agentmods.dev/badge/skills/open-octo/octo-agent/product-help/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/open-octo/octo-agent/product-help"><img src="https://agentmods.dev/badge/skills/open-octo/octo-agent/product-help.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,311 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Rogue Agent · line 16
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00091	$0.01311
Opus 5	$0.00046	$0.00656
Sonnet 5	$0.00018	$0.00262
Haiku 4.5	$0.00009	$0.00131

Measured 11d ago against content hash fe60f2f13359, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

product-help 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 11d 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.

internal/skills/defaults/product-help/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Help — answer octo usage questions from documentation

You have access to octo's product documentation. Use it to answer user questions accurately. Do not guess or hallucinate features.

Documentation sources

Bundled docs — check the skill directory for reference files. Each is a concise, offline-readable summary; most end with a link to the fuller online guide for depth (exact schemas, edge cases, worked examples) — follow that link with web_fetch when the summary doesn't fully answer the question, rather than guessing at the missing detail.
- README.md — quick start, installation, basic usage, feature overview
- CLI.md — command reference (octo, octo config, octo skills, octo workflows, octo browser, etc.)
- CONFIG.md — configuration file format and top-level fields
- SKILLS.md — the default-skill mechanism (embedding, precedence, octo skills) and how to write your own
- WORKFLOW.md — contributor development workflow for octo-agent's own codebase, git conventions, PR process (NOT the octo workflows product feature — see CLI.md for that)
- MCP.md — MCP server configuration (mcp.json, OAuth, Tool Search)
- MEMORY.md — cross-session memory (file layout, injection) and the optional external memory-backend feature
- PERMISSIONS.md — the permission engine (modes, rule format, per-session overrides)
- HOOKS.md — the hooks engine (hooks.yml, event types, blocking)
- IM.md — the IM/chat bridge (channels.yml, supported platforms, send_message/send_file)
- TUI.md — terminal UI reference (slash commands, keyboard shortcuts, status bar)
- WEB.md — Web UI reference (octo serve dashboard: composer shortcuts, mid-turn steer vs. queue)
- TROUBLESHOOTING.md — common issues and fixes
Read the relevant file(s) with read_file before answering.
Online docs (fallback, and the source of truth for anything the bundled summaries don't cover) — the public docs site at https://octo-agent.dev/docs/, fetched with web_fetch:
- guides/<topic>/ for narrative how-tos — e.g. guides/goals/, guides/workflows/, guides/loop/, guides/cron-tasks/, guides/browser-automation/, guides/sub-agents/, guides/expert-agents/, guides/light-apps/, guides/sandbox-the-agent/, guides/self-host/, guides/channels/, guides/hooks/, guides/use-skills/, guides/connect-mcp-servers/, guides/memory/, guides/memory-backends/
- reference/<topic>/ for exhaustive lookups — reference/cli/, reference/config-file/, reference/permissions/, reference/slash-commands/, reference/tools/, reference/http-api/, reference/security/, reference/compatibility/
- Some topics (sub-agents, expert-agents, light-apps, sandbox-the-agent, self-host) have a full guide online but no bundled summary file at all — go straight to web_fetch for those.
- For anything neither the bundled docs nor the docs site cover (e.g. an internal design doc under dev-docs/), fall back to https://github.com/open-octo/octo-agent/blob/main/<path> via web_fetch.

Read the full file on GitHub · 65 lines

Files

What ships with it

13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

11d ago First seen · 65 lines · 91 tokens per session scan A fe60f2f13359

Subscribe to this mod's changes

product-help is a skill published in the GitHub repository open-octo/octo-agent (97 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 1,311 once invoked, about $0.0005 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.

Learning and teaching agent ai-agent anthropic chatbot claude cli

baoyu-comic

A tool for creating educational comics from supplied text, files, links, or topics. It can cover explanations, biographies, and tutorials in different visual styles, tones, layouts, sizes, and languages.

StarryCod/cogitum · 17 tokens

manim-video

Manim CE animations: 3Blue1Brown math/algo videos.

StarryCod/cogitum · 19 tokens

ha-skill-creator

Create, edit, improve, or audit Hope Agent skills. Use when the user wants to: (1) create a new skill from scratch, (2) edit or improve an existing skill, (3) review or clean up a SKILL.md file, (4) run evaluations to test skill effectiveness, (5) optimize skill descriptions for better trigger accuracy. Trigger…

shiwenwen/hope-agent · 106 tokens

ha-mac-control

Hope Agent native macOS desktop control — the standard maccontrol status / diagnostics / apps / dock / spaces / snapshot / visual / windows / menu / clipboard / dialog loop, target-first action rules, no-blind-coordinate policy, and recovery for stale AX/window/menu/dialog state. Load whenever using maccontrol, or…

shiwenwen/hope-agent · 139 tokens

ha-browser

Hope Agent browser automation — the standard status → tabs → snapshot → act loop, stale-ref recovery rules, and what to do when login / 2FA / captcha / camera-prompt / dialog blocks progress. Load this skill whenever you reach for the browser tool. Trigger on: user asks the agent to open / control / click / scrape /…

shiwenwen/hope-agent · 140 tokens

ha-logs

A read-only troubleshooting skill for querying Hope Agent’s local SQLite databases, which store logs, conversations, and background-job status.

shiwenwen/hope-agent · 183 tokens