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 r007b34r/opencode-obsidian-knowledge-workflow --skill inbox-triagegit clone --depth 1 https://github.com/r007b34r/opencode-obsidian-knowledge-workflowWrote 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/r007b34r/opencode-obsidian-knowledge-workflow/inbox-triage)<a href="https://agentmods.dev/skills/r007b34r/opencode-obsidian-knowledge-workflow/inbox-triage"><img src="https://agentmods.dev/badge/skills/r007b34r/opencode-obsidian-knowledge-workflow/inbox-triage.svg" alt="Measured on agentmods" 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 | $0.00056 | $0.01102 |
| Opus 5 | $0.00028 | $0.00551 |
| Sonnet 5 | $0.00011 | $0.00220 |
| Haiku 4.5 | $0.00006 | $0.00110 |
Grade A, and why
inbox-triage 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 7d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
inbox-triage
Constraints
- NEVER scan whole vault; scope =
Inbox/or user-specified path only - NEVER write back without explicit user confirmation
- NEVER produce synthesis or thesis; output is routing decisions only
- NEVER deep-read all items; deep-read only when routing is genuinely uncertain
- MAX 20 items per batch; split and report remainder if more
Trigger Boundary
Use when: triage inbox, sort captures, route raw notes, process fleeting notes, decide what to promote/archive.
Do NOT use for:
- Cross-note relationship analysis →
connection-review - Week-level meaning extraction →
weekly-synthesis - Stable note creation →
note-promotion - Vault health diagnosis →
vault-health-feedback
Boundaries
- Owns: inbox routing, capture classification, shallow-read decisions
- Delegates to:
connection-review(items needing links),note-promotion(items marked promote) - Never absorbs: synthesis, health diagnosis, context maintenance, relationship analysis
Continuations
| Condition | Next skill |
|---|---|
| Promoted items with link potential > 2 | connection-review |
| Item marked promote-to-note, user confirms | note-promotion |
| Inbox path not found or empty | vault-health-feedback |
| Ambiguous items > 60% of batch | Escalate to human |
Companion Skill
All vault operations follow obsidian-mcp. Forbidden: obsidian_patch_note, obsidian_append_to_note. Verify every write through readback.
Procedure
Phase 1: Discover
obsidian_list_notes path:"Inbox/"→ candidate list- Count items; if >20, process first 20 and report remainder
Phase 2: Shallow Read
- For each:
obsidian_get_note format:"document-map"→ structure - Short notes (<500 words): read as
format:"content" - Flag genuinely uncertain items → mark
needs-deep-read
Phase 3: Classify
When classifying, read references/examples.md for decision calibration.
| Decision | Use when |
|---|---|
| keep-in-inbox | Too raw, still incubating |
| promote-to-note | Stable, reusable, independent |
| promote-to-idea | Personal observation worth preserving |
| move-to-project | Mainly useful inside active project |
| archive-or-ignore | Low-density, redundant, stale |
| needs-deep-read | Shallow evidence insufficient, potential value high |
What ships with it
6 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.
- 7d ago First seen · 126 lines · 56 tokens per session scan A 263b9d911627
inbox-triage is a skill published in the GitHub repository r007b34r/opencode-obsidian-knowledge-workflow (11 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,102 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
wiki-switch
Switch between multiple Obsidian wiki vault profiles. Use this skill when the user says "/wiki-switch NAME", "switch to my work wiki", "switch vault", "change wiki", "which wiki am I on", "list my wikis", "show my vaults", "create a new vault config", or "add a new wiki profile". The skill manages named config files…
knowledge-base-management
A lifecycle system for managing an Obsidian knowledge base, which is a folder of linked notes. It organizes raw material, AI-maintained wiki pages, and generated views into separate layers.
project
Create or maintain an Architecture Studio project — initialize its record bundle, remember sourced facts, capture or supersede decisions, inspect project status, or migrate a 1.x PROJECT.md. Use when the user says “set up the project,” “remember this,” “we decided,” asks about project context, or runs /as:project.
llm-wiki
Build and maintain an LLM-curated personal knowledge base — the "LLM Wiki" pattern from Andrej Karpathy's April 2026 gist. Use this skill whenever the user wants to ingest a source (paper, article, transcript, PDF, notes) into a persistent compounding knowledge base, ask a question against accumulated notes, lint or…
alive-morning
Morning briefing -- read all walnut states, surface priorities, inbox count, stale walnuts, people nudges.
pickup
Pick up work from repo-local handoff state. Use when starting a new Claude Code session, switching agents, returning to a project, or asking an AI agent to reconstruct context from prior work. Named pickup rather than resume to avoid shadowing Claude Code's built-in /resume conversation picker.