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 AdrianV101/obsidian-pkm-plugin --skill triage-tasksgit clone --depth 1 https://github.com/AdrianV101/obsidian-pkm-pluginWrote 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/adrianv101/obsidian-pkm-plugin/triage-tasks)<a href="https://agentmods.dev/skills/adrianv101/obsidian-pkm-plugin/triage-tasks"><img src="https://agentmods.dev/badge/skills/adrianv101/obsidian-pkm-plugin/triage-tasks/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/adrianv101/obsidian-pkm-plugin/triage-tasks"><img src="https://agentmods.dev/badge/skills/adrianv101/obsidian-pkm-plugin/triage-tasks.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 | $0.00027 | $0.01230 |
| Opus 5 | $0.00014 | $0.00615 |
| Sonnet 5 | $0.00005 | $0.00246 |
| Haiku 4.5 | $0.00003 | $0.00123 |
Grade A, and why
triage-tasks scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage Tasks — Surface and Batch-Update Open Vault Tasks
Runs interactively: fetch open tasks, show them numbered with completion hints, wait for user decisions, apply updates.
Step 1: Determine Scope
Detect the current project from CLAUDE.md:
Read("CLAUDE.md") // look for: # PKM: <path>
Extract the vault project path from a line matching /^#\s+PKM:\s*(.+)$/m (e.g., 01-Projects/Obsidian-MCP).
Scope (check skill args first, then default):
- Current project (default): use the detected project folder
- All (if args contain "all" or no project detected and user chooses all): omit
folderfrom queries
If CLAUDE.md has no # PKM: line and no scope was specified, ask:
"No project found in CLAUDE.md. Should I triage tasks across all projects, or a specific folder?"
Step 2: Fetch Open Tasks
vault_query({ type: "task", status: "pending", folder: "<project>", sort_by: "priority", sort_order: "desc" })
vault_query({ type: "task", status: "active", folder: "<project>", sort_by: "priority", sort_order: "desc" })
Omit folder for all-projects scope. If both return empty, report "No open tasks found — all clear!" and stop.
Combine: active tasks first (priority-sorted), then pending (priority-sorted). Assign sequential numbers 1–N.
Step 3: Gather Completion Hints
Collect lightweight signals in two calls — not one call per task.
Activity log (check if any task was recently touched):
vault_activity({ since: "<date 30 days ago as YYYY-MM-DD>", limit: 100 })
Git log (look for commits related to task work):
Bash: git rev-parse --is-inside-work-tree 2>/dev/null && git log --oneline --since="30 days ago" | head -50
If git rev-parse fails (not a git repo), skip git hints silently — don't surface an error to the user.
For each task, derive a hint from these results:
- Task path appears in the activity log with a write tool (
vault_update_frontmatter,vault_edit,vault_append): mark "recently updated" - Any word from the task's filename (≥ 4 chars, case-insensitive, split on
-) appears in a commit message: mark "⚡ git commits" - Neither: no hint (omit hint entirely)
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.
- 10d ago First seen · 140 lines · 27 tokens per session scan A bcedea242375
triage-tasks is a skill published in the GitHub repository AdrianV101/obsidian-pkm-plugin (13 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 1,230 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
project-sync
On-demand AI-powered sync of a project's repo state into the brain vault. Reads live git/GitHub/Jira data, updates the project status doc, and makes targeted edits to relevant brain docs where content is clearly stale. Triggered by "/project-sync [name]", "sync [project]", "what's the current state of [project]".
owd-albatross
Connect, initialize, resume, or coordinate MDevolved Projects from Albatross using its agent.config.json stdio MCP surface, a pinned OAuth bridge, qualified tool names, workspace prompt continuity, path forks, resets, and independently attributable participant identities. Use when a repository runs Albatross, contains…
owd-eve
Connect, initialize, resume, or coordinate MDevolved Projects from an Eve agent using Eve's standard remote MCP connection, user-scoped Vercel Connect OAuth, qualified tool names, durable Project continuity, and independently attributable agent identities. Use when an Eve repository has agent/connections, when adding…
log-decision
Log cross-cutting business/product/hiring/vendor decisions to decisions/ directory with context and alternatives.
mdevolved-eve
Connect or resume an Eve agent with MDevolved through a user-scoped remote MCP connection while preserving Eve runtime identity and MDevolved Project continuity.
design-mcp-server
Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.