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-tasks-extractgit 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-tasks-extract)<a href="https://agentmods.dev/skills/ihudak/ihudak-claude-plugins/wiki-tasks-extract"><img src="https://agentmods.dev/badge/skills/ihudak/ihudak-claude-plugins/wiki-tasks-extract/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-tasks-extract"><img src="https://agentmods.dev/badge/skills/ihudak/ihudak-claude-plugins/wiki-tasks-extract.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 | $0.00098 | $0.01675 |
| Opus 5.5 | $0.00039 | $0.00670 |
| Sonnet 5.5 | $0.00020 | $0.00335 |
| Haiku 4.5 | $0.00010 | $0.00168 |
Grade A, and why
wiki-tasks-extract 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 2mo 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wiki-tasks-extract
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-tasks-extract [wiki-path]
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 — Determine wiki path
| Argument | Resolved path |
|---|---|
| (none) | wiki/ (vault root wiki) |
Relative path (e.g. Projects/Products/MyProject/wiki/) |
As given, relative to vault root |
| Absolute path | Use directly |
Validate:
- The directory exists
- It contains
_log.mdor_index.md(confirming it is a wiki directory)
If invalid, report the error and stop.
Identify the project context: if the wiki path is under
Projects/<Category>/<project>/, remember this project for target-file
matching in Step 7.
Step 3 — Phase A: Harvest flagged action items
Read <wiki-path>/_log.md. Extract every line matching:
- Action items flagged: <description>
For each, record:
- The description text
- The source file from the log entry heading
(the log format is
## [YYYY-MM-DD] ingest | <source-file>followed by bullet points) - The date from the log entry heading
- Any surrounding context (decisions, people mentioned, technologies)
Skip any action item that appears in a previous tasks-extract log entry
(heading format: ## [YYYY-MM-DD] tasks-extract | ...). This prevents
re-extraction on subsequent runs.
These are high-confidence candidates — the ingest process already identified them as action items.
Step 4 — Phase B: Semantic scan
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.
- 2mo ago First seen · 214 lines · 98 tokens per session scan A cff66022ad7f
wiki-tasks-extract is a skill published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 1,675 once invoked, about $0.0004 per session on Opus 5.5. 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.
wiki-tasks-extract compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| wiki-tasks-extractihudak/ihudak-claude-plugins | Skill | 2 | 1mo ago | MIT | A | 98 | Claude Code |
| competitive-battlecardphuryn/pm-skills | Skill | 28k | 8d ago | MIT | A | 52 | Claude Code |
| bun-test-mockingsecondsky/claude-skills | Skill | 245 | 6d ago | MIT | A | 25 | Claude Code |
| handoffAvijit07x/claude-db | Skill | 233 | 15d ago | Apache-2.0 | A | 87 | Claude Code, Codex |
| stress-test-methodologyoborchers/fractional-cto | Skill | 36 | 12d ago | MIT | A | 92 | Claude Code |
| run-planjuliusz-cwiakalski/agentic-delivery-os | Skill | 43 | yesterday | MIT | A | 11 | Claude Code |
| creative-directioneugenelim/agent-ready-repo | Skill | 28 | yesterday | Apache-2.0 | A | 210 | Claude Code |