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 channel-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/channel-manager)<a href="https://agentmods.dev/skills/open-octo/octo-agent/channel-manager"><img src="https://agentmods.dev/badge/skills/open-octo/octo-agent/channel-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/channel-manager"><img src="https://agentmods.dev/badge/skills/open-octo/octo-agent/channel-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 19 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 Privilege Escalation · line 37 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 58 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 140 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 293 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 304 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 431 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Tool Misuse · line 194 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 Data Exfiltration · line 123 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Rogue Agent · line 208 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 Privilege Escalation · line 247 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 298 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 321 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 341 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 374 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 402 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Data Exfiltration · line 316 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Privilege Escalation · line 419 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 455 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Rogue Agent · line 419 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 | $0.00225 | $0.06564 |
| Opus 5 | $0.00112 | $0.03282 |
| Sonnet 5 | $0.00045 | $0.01313 |
| Haiku 4.5 | $0.00022 | $0.00656 |
Grade B, and why
channel-manager scanned grade B with 2 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 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
6. Merge into `~/.octo/channels.yml` (preserve other platforms), then `chmod 600 ~/.octo/channels.yml`: Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST "http://127.0.0.1:8088/api/channels/<platform>/reload" How it starts
The opening of the file, as written. The whole thing — 457 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Channel Manager Skill
Terminology
When conversing in Chinese, refer to a user-created agent profile as 专家 (not 智能体) when asking whether to bind a channel instance to one — matches the desktop/web UI's Chinese labels. English conversations keep "agent".
Configure IM platform channels for octo. Supported platforms: feishu, weixin, wecom, dingtalk, discord, telegram.
How channels work in octo
- Config lives in
~/.octo/channels.yml(YAML, mode 600). Edit it directly withread_file/write_file. - Each platform can have multiple bot instances — e.g. 3 Feishu bots in one group,
each bound to a different expert agent. Instances are named; the name becomes the
adapter_idused in profilechannel_bindings. - Adapters run inside
octo serve, started alongside the HTTP server (skip with--no-channel). Config changes are applied on save viaPOST /api/channels/<platform>— no full restart needed. - Weixin login state lives separately in
~/.octo/weixin-credentials.json, written by the QR-login flow this skill drives (POST /api/channels/weixin/loginon the running serve).
channels.yml schema (multi-instance):
channels:
feishu:
- name: code-review-bot # instance name (adapter_id); omit for single-instance
enabled: true | false
app_id: string # required
app_secret: string # required
domain: string # optional, default https://open.feishu.cn
allowed_users: string # optional, comma-separated user IDs; empty = allow all
- name: ops-bot # second instance, same platform
enabled: true
app_id: ...
app_secret: ...
weixin:
- enabled: true | false
token: string # bot token; optional if cred_path exists
cred_path: string # optional, default ~/.octo/weixin-credentials.json
base_url: string # optional, default https://ilinkai.weixin.qq.com
allowed_users: string
dingtalk:
- name: ... # optional
enabled: true | false
client_id: string # required (AppKey)
client_secret: string # required (AppSecret)
allowed_users: string
wecom:
- name: ...
enabled: true | false
bot_id: string # required, intelligent robot Bot ID (starts with "aib")
secret: string # required, robot secret
allowed_users: string
discord:
- name: ...
enabled: true | false
bot_token: string # required, from the Discord Developer Portal
allowed_users: string
telegram:
- name: ...
enabled: true | false
bot_token: string # required, from @BotFather
base_url: string # optional, default https://api.telegram.org
parse_mode: string # optional, default "Markdown"; empty string disables
allowed_users: string
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 · 457 lines · 225 tokens per session scan B c7f3c789b4a1
channel-manager is a skill published in the GitHub repository open-octo/octo-agent (99 stars, last pushed yesterday), licensed MIT. It adds 225 tokens to every session and 6,564 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, 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-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-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-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-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…
feishu
A toolkit for working with Feishu, also called Lark, a workplace collaboration platform. It covers documents, spreadsheets, files, wikis, approvals, calendars, and contacts.