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 0xranx/golembot --skill task-managergit clone --depth 1 https://github.com/0xranx/golembotWrote 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/0xranx/golembot/task-manager)<a href="https://agentmods.dev/skills/0xranx/golembot/task-manager"><img src="https://agentmods.dev/badge/skills/0xranx/golembot/task-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/0xranx/golembot/task-manager"><img src="https://agentmods.dev/badge/skills/0xranx/golembot/task-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 77 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 27 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.
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 | $0.00048 | $0.00752 |
| Opus 5.5 | $0.00019 | $0.00301 |
| Sonnet 5.5 | $0.00010 | $0.00150 |
| Haiku 4.5 | $0.00005 | $0.00075 |
Grade A, and why
task-manager scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST http://localhost:$PORT/api/tasks \ How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Manager
You can create and manage scheduled tasks for the user. When the user asks you to do something periodically (e.g. "every morning at 9am, summarize my emails"), create a scheduled task via the Task HTTP API.
Recognizing Task Intent
Watch for phrases like:
- "every day/week/hour..."
- "remind me to..."
- "at 9am, do..."
- "schedule a task..."
- "periodically check..."
- "set up a cron job..."
- "create a recurring..."
- "set a timer for..."
Creating a Task
Use the Task HTTP API (running on the gateway's port):
curl -X POST http://localhost:$PORT/api/tasks \
-H "Content-Type: application/json" \
-d '{
"name": "daily-summary",
"schedule": "0 9 * * *",
"prompt": "Summarize the key updates from today",
"enabled": true,
"target": {
"channel": "feishu",
"chatId": "oc_xxxx"
}
}'
Validation
Before creating a task, verify:
- The
schedulefield is a valid 5-field cron expression - The
promptis non-empty and specific enough to produce useful output when run unattended - If a
targetis provided,channelis required;chatIdis optional (if omitted, the result is sent to all known chats on that channel)
If the API returns an error (non-2xx status), report the failure to the user with the error message rather than assuming success.
TaskRecord Schema
| Field | Type | Required | Description |
|---|---|---|---|
name |
string | yes | Human-readable task name |
schedule |
string | yes | Cron expression (see below) |
prompt |
string | yes | The prompt sent to the agent when the task fires |
enabled |
boolean | no | Default: true |
target |
object | no | Where to deliver the result |
target.channel |
string | yes* | Channel name: feishu, dingtalk, wecom, slack, telegram, discord, weixin |
target.chatId |
string | no | Chat/conversation ID. If omitted, sends to all known chats on the channel |
Common Cron Expressions
| Expression | Meaning |
|---|---|
0 9 * * * |
Every day at 9:00 AM |
0 9 * * 1-5 |
Weekdays at 9:00 AM |
*/30 * * * * |
Every 30 minutes |
0 */2 * * * |
Every 2 hours |
0 9 * * 1 |
Every Monday at 9:00 AM |
0 0 1 * * |
First day of each month at midnight |
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.
- 1mo ago First seen · 79 lines · 48 tokens per session scan A e0270d811147
task-manager is a skill published in the GitHub repository 0xranx/golembot (323 stars, last pushed 24d ago), licensed MIT. It adds 48 tokens to every session and 752 once invoked, about $0.0002 per session on Opus 5.5. 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
give-me-tips
Explains any senpi tip in depth, including Tip: lines in the TUI. Use when the user asks about a tip, what a tipped feature does, or which tips they can see.
ponytail-gain
Show ponytail's measured impact as a compact scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot display, not a persistent mode, and not a per-repo number. Trigger: /ponytail-gain, "ponytail gain", "what does ponytail save", "show ponytail impact", "ponytail scoreboard".
project-memory-keeper
Analyzes the last session to log progress, extract lessons learned, and save them to the project memory instructions.
cursor-delegate
Delegate bounded light-to-medium implementation, investigation, documentation, configuration, testing, and tooling work to Cursor Bridge after the primary agent owns direction and risk boundaries. Also use when the user explicitly asks to create, keep, continue, inspect, or close the same Cursor execution session…
oculpm-journal
A work-journal format for recording coding-agent tasks, including bugs, features, errors, refactors, and chores. It defines where files go and what information each record must contain.
audio-dispatch
Transcribe a multi-speaker recording with Voxtral and summarize decisions, actions, and open questions by speaker. Use for meeting or call recordings that need speaker attribution.