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 agentmods add skills/vanillaflava/tasknotes-skill/tasknotesnpx skills add vanillaflava/tasknotes-skill --skill tasknotesgit clone --depth 1 https://github.com/vanillaflava/tasknotes-skillWhat 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 | $0.00120 | $0.05364 |
| Opus 5 | $0.00060 | $0.02682 |
| Sonnet 5 | $0.00024 | $0.01073 |
| Haiku 4.5 | $0.00012 | $0.00536 |
Grade A, and why
tasknotes 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 yesterday.
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 — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TaskNotes
Multi-modal task management for Obsidian TaskNotes vaults. The skill probes the environment first and routes to the best available access method.
Step 0 - Environment probe
Run before any operation. Determines which path to take.
Bundled help: This skill includes references/tasknotes-help.md with step-by-step setup instructions, full API endpoint reference, and troubleshooting for all failure modes. Read it yourself when connection or setup issues arise, and share the relevant sections with the user to guide them through fixes.
1. MCP available?
Run tool_search("tasknotes"). If tasknotes: tools load successfully, the MCP server is live.
2. HTTP API available?
Attempt web_fetch("http://localhost:8080/api/health"). If the response contains {"status":"ok",...}, the HTTP API is live on port 8080.
If the request fails (connection refused or timeout), ask the user:
- "What port is your TaskNotes HTTP API configured on? Check Settings → TaskNotes → Integrations → HTTP API."
- "Are both the HTTP API toggle and the MCP Server toggle enabled in those settings?"
Try the user-supplied port before giving up. If still unreachable, HTTP API is unavailable.
3. Filesystem available?
Check whether any loaded tool can read and write .md files. Do not assume a specific tool name - any filesystem capability qualifies.
Routing
| MCP | HTTP API | Filesystem | Route |
|---|---|---|---|
| Yes | - | - | MCP for all ops including body reads (fixed in v4.8.0) |
| No | Yes | - | HTTP API for all frontmatter and body ops |
| No | No | Yes | Filesystem path - all workflows below |
| No | No | No | Inform user what is missing; link references/tasknotes-help.md for setup |
What works on which surface
| Operation | MCP | HTTP API | Filesystem |
|---|---|---|---|
| Create task | tasknotes_create_task |
POST /api/tasks |
Workflow 1 |
| Update frontmatter | tasknotes_update_task |
PUT /api/tasks/:id |
Workflow 3 |
| Mark done | tasknotes_update_task |
PUT /api/tasks/:id |
Workflow 4 |
| Query / filter tasks | tasknotes_query_tasks |
POST /api/tasks/query |
Workflow 5 |
| Read task frontmatter | tasknotes_get_task |
GET /api/tasks/:id |
Read .md file |
| Read task body / checklist | tasknotes_get_task (details field) |
GET /api/tasks/:id |
Read .md file |
| Write task body | tasknotes_update_task (details field) |
PUT /api/tasks/:id |
Write .md file |
| Complete recurring instance | tasknotes_complete_recurring_instance |
POST /api/tasks/:id/complete-instance |
Not supported (GUI only) |
| Schema diagnostic | ✗ → Workflow 9 | ✗ → Workflow 9 | Workflow 9 |
| Time tracking | tasknotes_*_time_tracking |
/api/tasks/:id/time/* |
Manual (complex) |
| Pomodoro | tasknotes_*_pomodoro |
/api/pomodoro/* |
Not supported |
| Works when Obsidian closed | ✗ | ✗ | ✓ |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 458 lines · 120 tokens per session scan A 5216f1bc1fd1
tasknotes is a skill published in the GitHub repository vanillaflava/tasknotes-skill (14 stars, last pushed 2mo ago), licensed MIT. It adds 120 tokens to every session and 5,364 once invoked, about $0.0006 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
analyze-document
Forensically analyse a family court document using the 13-point protocol. Use when the user says "analyse this document", "review this affidavit", "what does this report say", "break down this letter", uploads a court document, affidavit, family report, solicitor letter, or any legal document related to their family…
case-setup
Set up a new family court case vault from scratch. Use when the user says "set up my case", "start my case vault", "I need to organise my family court case", "help me build a case", "create my evidence vault", or is beginning a new family court matter and needs structure.
case-strategy
Develop legal strategy and identify next steps based on the evidence vault. Use when the user says "what should I do next", "build my strategy", "prepare for court", "what are my options", "how strong is my case", "prepare for the hearing", "what arguments can I make", "help me with my variation application", or needs…
evidence-review
Cross-reference evidence across the entire case vault to find contradictions, patterns, and gaps. Use when the user says "review my evidence", "find contradictions", "what patterns do you see", "cross-reference my documents", "update the evidence matrix", "what am I missing", "analyse my whole case", or wants a…
lawyer-accountability
Track and evaluate solicitor performance, costs, and accountability. Use when the user says "is my lawyer doing their job", "track my legal costs", "review my solicitor's advice", "hold my lawyer accountable", "was I properly represented", "review the settlement process", "check my legal bills", or has concerns about…
obsidian-companion
Use when interacting with the user's Obsidian vault — reading, writing, searching, or chatting with notes using local RAG. Guides tool selection and writing strategy for all vault operations.