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 skills add open-octo/octo-agent --skill expert-agent-managergit clone --depth 1 https://github.com/open-octo/octo-agentWrote 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/skills/open-octo/octo-agent/expert-agent-manager)<a href="https://agentmods.dev/skills/open-octo/octo-agent/expert-agent-manager"><img src="https://agentmods.dev/badge/skills/open-octo/octo-agent/expert-agent-manager/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/skills/open-octo/octo-agent/expert-agent-manager"><img src="https://agentmods.dev/badge/skills/open-octo/octo-agent/expert-agent-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
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 →
- high Tool Misuse · line 143 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 357 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Rogue Agent · line 4 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.
- medium Rogue Agent · line 108 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.
- medium Rogue Agent · line 316 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.
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 | $0.00121 | $0.05282 |
| Opus 5 | $0.00060 | $0.02641 |
| Sonnet 5 | $0.00024 | $0.01056 |
| Haiku 4.5 | $0.00012 | $0.00528 |
Grade A, and why
expert-agent-manager 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 7d 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.
Use `curl` via the `terminal` tool to call them. (Do NOT use `web_fetch` — How it starts
The opening of the file, as written. The whole thing — 420 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage Agent Profiles
Terminology
When conversing in Chinese, refer to this concept as 专家 (not 智能体, and
not a bare "agent") — this matches the desktop/web UI's Chinese labels
(创建专家 / 编辑专家 / 删除专家). English conversations keep "agent". This is
a conversational naming convention only — API fields, IDs, and code
identifiers (agent_id, /api/agents, etc.) are unaffected.
octo's multi-agent system lets users define agent profiles — each with its
own system prompt, model, tool allowlist, and IM chat bindings. User-created
profiles are stored as Markdown files in ~/.octo/agents/<id>.md (body =
system prompt, YAML frontmatter = metadata).
This skill manages profiles by calling the REST API on the running octo server. It is only available to the Default Agent — expert agents cannot create or modify profiles (they can only enable/disable from their own allowlist).
Curated vs. user-created experts
GET/POST/PUT/DELETE on /api/agents see two kinds of profile,
distinguished by a source field on every response:
-
"source": "user"— created via this skill or the Web UI form, stored in~/.octo/agents/. Freely editable and deletable. -
"source": "default"— an officially curated expert shipped in the binary (the ones shown in the Web UI's expert gallery, e.g. copywriter, resume-coach, trip-planner). These are read-only:PUTandDELETEon one both refuse. They can only be hidden. An official expert is identical on every machine and keeps receiving content updates when octo ships a new curated-persona revision — editing one used to fork it into a~/.octo/agents/<id>.mdoverride and silently forfeit those updates, which is why it no longer does.When the user asks to change a curated expert, don't try to edit it: create a NEW user agent (a different id) with the persona they want, and say plainly that the official one stays as shipped and can be hidden if they'd rather not see both. A user file at a curated expert's id is ignored on load, so writing one by hand achieves nothing either.
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.
- 7d ago Changed · +3 lines 2fef62c50151
- 11d ago First seen · 417 lines · 121 tokens per session scan A 67a59ffb5da8
expert-agent-manager is a skill published in the GitHub repository open-octo/octo-agent (97 stars, last pushed today), licensed MIT. It adds 121 tokens to every session and 5,282 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
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…
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…
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 /…
ha-logs
A read-only troubleshooting skill for querying Hope Agent’s local SQLite databases, which store logs, conversations, and background-job status.
ha-data-analytics
A local-first data-analysis and reporting skill for CSV and spreadsheet files. It produces decision-ready analyses and shareable offline reports while separating facts, calculations, interpretations, and recommendations.
ha-pet-import
Safely import, select, switch, or enable a compatible desktop pet in Hope Agent. Resolve packages from any origin, including local folders, zip archives, pet.json plus a sprite, PNG/WebP atlases, chat attachments, repository or cloud files, direct HTTPS artifact URLs, and download pages. Use whenever a user asks to…