weekly-synthesis

weekly-synthesis is a skill for Claude Code, Codex from r007b34r/opencode-obsidian-knowledge-workflow. It costs 63 tokens per session (1,141 once invoked), scanned A, original, Apache-2.0.

A weekly review for recent Obsidian notes, which are linked knowledge records. It extracts an emerging idea, supporting evidence, conflicts, missing information, one action, and one question from a chosen time period.

In plain words
What is it for?
Use it to understand what recent notes mean, find an emerging thesis, identify gaps, and choose the next action and question. By default it reviews the last seven days and does not directly change notes.
Why use it?
It turns a pile of recent notes into a focused interpretation instead of a simple recap. When the evidence is weak, it says the conclusion is uncertain rather than forcing one.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/r007b34r/opencode-obsidian-knowledge-workflow/weekly-synthesis
Any agent
npx skills add r007b34r/opencode-obsidian-knowledge-workflow --skill weekly-synthesis
Clone the repo
git clone --depth 1 https://github.com/r007b34r/opencode-obsidian-knowledge-workflow

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for weekly-synthesis

README.md
[![agentmods](https://agentmods.dev/badge/skills/r007b34r/opencode-obsidian-knowledge-workflow/weekly-synthesis.svg)](https://agentmods.dev/skills/r007b34r/opencode-obsidian-knowledge-workflow/weekly-synthesis)
Your own site
<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>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,141 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 5d ago against content hash e071992952d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 2 executable files (validators/post-check.sh, validators/pre-check.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/weekly-synthesis/SKILL.md · 124 lines

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

  1. Identify time window (default: 7 days; respect user-specified period)
  2. obsidian_list_notes or obsidian_search_notes → notes in window
  3. Count and report scope before proceeding

Phase 2: Read

  1. obsidian_get_note format:"document-map" → theme distribution
  2. Deep-read only notes that support thesis, contradiction, or gap claims
  3. Use older notes only for calibration (not primary signal)

Read the full file on GitHub · 124 lines

Files

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.

Changes

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.

  1. 5d ago First seen · 124 lines · 63 tokens per session scan A e071992952d1

Subscribe to this mod's changes

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.

Related

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.

AlpacaLabsLLC/skills-for-architects · 69 tokens

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…

praneybehl/llm-wiki-plugin · 221 tokens

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…

harnessprotocol/harness-kit · 80 tokens

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.

harnessprotocol/harness-kit · 76 tokens

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…

harnessprotocol/harness-kit · 73 tokens

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…

tejpalv/cc-wiki · 76 tokens