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 ihudak/ihudak-claude-plugins --skill wiki-taskgit clone --depth 1 https://github.com/ihudak/ihudak-claude-pluginsWrote 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/ihudak/ihudak-claude-plugins/wiki-task)<a href="https://agentmods.dev/skills/ihudak/ihudak-claude-plugins/wiki-task"><img src="https://agentmods.dev/badge/skills/ihudak/ihudak-claude-plugins/wiki-task/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/ihudak/ihudak-claude-plugins/wiki-task"><img src="https://agentmods.dev/badge/skills/ihudak/ihudak-claude-plugins/wiki-task.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 | $0.00079 | $0.01730 |
| Opus 5 | $0.00039 | $0.00865 |
| Sonnet 5 | $0.00016 | $0.00346 |
| Haiku 4.5 | $0.00008 | $0.00173 |
Grade A, and why
wiki-task 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wiki-task
Read these files fully before proceeding:
skills/_shared/task-rules.mdskills/_shared/vault-conventions.md
Then attempt to read .obsidian/copilot/tag-index.md (at vault root).
If the file does not exist, note it and continue — tags will be omitted from tasks.
See the "If tag-index.md does not exist" section in task-rules.md.
Invoke with: /wiki-task <description>
Step 1 — Resolve VAULT_PATH
Vault path: ~/obsidian_vault by default; set VAULT_PATH to override.
WSL users with a Windows-side vault must set VAULT_PATH explicitly
(e.g. /mnt/c/Users/<name>/obsidian_vault).
All file paths below are relative to the vault root.
Step 2 — Parse the prompt
Analyse the natural-language <description> and extract every field you can.
Do not ask follow-up questions for fields that are simply absent — leave them
at their defaults. Only ask the user when the prompt is genuinely ambiguous
(e.g., two plausible target projects).
2.1 — Description text
The core task description. Strip out metadata you extract into other fields (dates, priority words, effort hints) so the description reads cleanly.
2.2 — Effort estimate
Map effort hints to Fibonacci values using the scale in task-rules.md.
Heuristics:
- Explicit numbers or words: "5 min" →
[0], "quick" →[0]–[1], "half a day" →[3], "a few days" →[5], "a week" →[8]. - Action verbs: "review" / "approve" / "check" → lean
[0]–[1]; "implement" / "build" / "migrate" → lean[2]–[5]; "design" / "architect" → lean[3]–[8]. - If truly no signal: use
[ ](unestimated). - When in doubt between two values, pick the higher one.
2.3 — Priority
Look for: "urgent", "critical", "highest", "high", "low", "lowest",
"asap", "blocking", "nice to have", "backlog".
Map to the priority emoji from task-rules.md. Default: none (Normal).
2.4 — Dates
- Scheduled date (
⏳): "start on", "begin", "from", "starting" - Due date (
📅): "due", "by", "before", "deadline", "until" - Relative dates: "today", "tomorrow", "next Monday", "in two weeks",
"end of month" — resolve to
YYYY-MM-DDusing the current date. - Always add
➕ <today>(created date).
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.
- 3d ago First seen · 207 lines · 79 tokens per session scan A fc9ef82fc70c
wiki-task is a skill published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed 6d ago), licensed MIT. It adds 79 tokens to every session and 1,730 once invoked, about $0.0004 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 2026-09-05.
Other skills, from other repositories
recipe-block-focus-time
Create recurring focus time blocks on Google Calendar to protect deep work hours.
recipe-organize-drive-folder
Create a Google Drive folder structure and move files into the right locations.
recipe-schedule-recurring-event
Create a recurring Google Calendar event with attendees.
gws-workflow
Google Workflow: Cross-service productivity workflows.
recipe-find-free-time
Query Google Calendar free/busy status for multiple users to find a meeting slot.
recipe-review-overdue-tasks
Find Google Tasks that are past due and need attention.