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/r007b34r/opencode-obsidian-knowledge-workflow/weekly-synthesisnpx skills add r007b34r/opencode-obsidian-knowledge-workflow --skill weekly-synthesisgit 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/weekly-synthesis)<a href="https://agentmods.dev/skills/r007b34r/opencode-obsidian-knowledge-workflow/weekly-synthesis"><img src="https://agentmods.dev/badge/skills/r007b34r/opencode-obsidian-knowledge-workflow/weekly-synthesis.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 | $0.00063 | $0.01141 |
| Opus 5 | $0.00032 | $0.00571 |
| Sonnet 5 | $0.00013 | $0.00228 |
| Haiku 4.5 | $0.00006 | $0.00114 |
Grade A, and why
weekly-synthesis 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 5d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
weekly-synthesis
Constraints
- Output is NOT a recap; must contain thesis + evidence
- EXACTLY one action, EXACTLY one question (not zero, not many)
- NEVER let old notes dominate; they are calibration only
- NEVER write synthesis note without user confirmation
- If signal is weak: say "conclusion is uncertain" — do NOT force a thesis
- Default time window: 7 days unless user specifies otherwise
Trigger Boundary
Use when: weekly synthesis, what recent notes mean, emerging thesis, one most valuable next action/question, time-window meaning-making.
Do NOT use for:
- Raw material routing →
inbox-triage - Link-only or relationship review →
connection-review - Project status reporting (not synthesis)
- Promoting result into stable note →
note-promotion
Boundaries
- Owns: time-window meaning extraction, thesis formation, gap identification
- Delegates to:
note-promotion(synthesis ready for stable note),opencode-context-maintenance(thesis reveals drift) - Never absorbs: inbox routing, link-only review, health diagnosis
Continuations
| Condition | Next skill |
|---|---|
| User wants to preserve synthesis as stable note | note-promotion |
| Thesis or gaps reveal context drift | opencode-context-maintenance |
| Insufficient signal; try relationships first | connection-review |
| Signal too weak to form any thesis | 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: Scope
- Identify time window (default: 7 days; respect user-specified period)
obsidian_list_notesorobsidian_search_notes→ notes in window- Count and report scope before proceeding
Phase 2: Read
obsidian_get_note format:"document-map"→ theme distribution- Deep-read only notes that support thesis, contradiction, or gap claims
- Use older notes only for calibration (not primary signal)
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.
- 5d ago First seen · 124 lines · 63 tokens per session scan A e071992952d1
weekly-synthesis 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 63 tokens to every session and 1,141 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
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…
orient
Use when user invokes /orient with a topic keyword, entity type, project name, time qualifier, or combination. Also triggers on "what do we know about X", "remind me about X", "where did we leave off on X". Provides targeted context loading — searches the MCP Memory Server graph, knowledge files, journal entries, and…
memory
Use when user invokes /memory with a subcommand (search, trace, add, episode, status). Also triggers on "search my memory for X", "add to memory", "what do I know about X" (when membrain is available), "memory status", "memory trace". Searches and manages the membrain knowledge graph via MCP tools or HTTP API.
capture
Use when user invokes /capture to capture information from the current conversation into a staging file for later reflection and knowledge graph processing. Accepts no arguments (auto-extract), specific facts as text, or filter keywords like "decisions" or "technical". Do NOT use when the user wants to write directly…
cc-wiki
Distill the user's /.claude history into a Quartz knowledge base. Runs preprocess.py, dispatches parallel project-digest agents, then parallel cross-cutting synthesis agents (people / companies / projects / concepts / workflows / tools / playbooks), writes the spine, installs Quartz, and starts the dev server. Single…