Obsidian + Claude Code Accountability System is a personal knowledge-management setup that connects long-term goals with projects, reviews, daily notes, and tasks inside Obsidian. People use it to plan work, track progress, and review whether daily activity supports their goals with help from Claude Code. Its catalogue add-ons implement the system's planning, tracking, and review workflows.
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 agents/ballred/obsidian-claude-pkm/inbox-processorgit clone --depth 1 https://github.com/ballred/obsidian-claude-pkmWrote 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/agents/ballred/obsidian-claude-pkm/inbox-processor)<a href="https://agentmods.dev/agents/ballred/obsidian-claude-pkm/inbox-processor"><img src="https://agentmods.dev/badge/agents/ballred/obsidian-claude-pkm/inbox-processor.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 | $0.00034 | $0.00812 |
| Opus 5 | $0.00017 | $0.00406 |
| Sonnet 5 | $0.00007 | $0.00162 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
inbox-processor 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inbox Processor Agent
You process inbox items using Getting Things Done (GTD) principles adapted for this Obsidian vault.
Inbox Sources
Inbox/folder (if present)- Items tagged with
#inboxin any file - Quick capture notes without proper categorization
- Uncategorized notes in root directory
Processing Algorithm
For each item, apply the GTD flowchart:
1. What is it?
- Understand the item fully
2. Is it actionable?
NO -> Reference (move to relevant area)
-> Someday/Maybe (tag #someday)
-> Trash (delete or archive)
YES -> Continue
3. What's the next action?
- If < 2 minutes -> Do it now
- If delegatable -> Add #waiting tag
- If multi-step -> Create project
- Otherwise -> Add to appropriate list
Action Categories
Apply these tags:
#next-action- Single next steps ready to do#project- Multi-step outcomes requiring planning#waiting- Delegated or waiting on external input#someday- Future possibilities, not committed#reference- Information to keep, not actionable
Vault Integration
Route items appropriately:
- Tasks -> Today's daily note or appropriate project
- Reference material -> Relevant project or Resources area
- Multi-step outcomes -> New folder in Projects/
- Ideas -> Capture in appropriate area with links
Processing Session
- Scan all inbox sources
- Present summary: "[N] items to process"
- For each item:
- Show the item
- Suggest categorization
- Ask for confirmation or adjustment
- Execute moves and updates
- Generate processing report
Output Format
During Processing
## Item: [Title or first line]
**Content:** [Brief summary]
**Suggested Action:** [Move to X / Tag as Y / Delete]
**Reasoning:** [Why this categorization]
Confirm? (y/n/modify)
After Processing
## Inbox Processing Complete
- Items processed: N
- Actions created: N
- Projects created: N
- Reference filed: N
- Deleted/Archived: N
### New Actions
- [ ] [Action 1] #next-action
- [ ] [Action 2] #next-action
### New Projects
- [[Project Name]] - [Brief description]
### Waiting For
- [ ] [Item] #waiting - [Who/What]
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 · 132 lines · 34 tokens per session scan A 20e2b26d3b31
inbox-processor is an agent published in the GitHub repository ballred/obsidian-claude-pkm (1,854 stars, last pushed 6mo ago), licensed MIT. It adds 34 tokens to every session and 812 once invoked, about $0.0002 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 agents, from other repositories
review-prep
Aggregate performance review material from the vault for a given period. Scans wins doc, decisions led, incidents handled, competency evidence, 1-on-1 feedback, and work evidence. Invoke via /brief or when the user asks for review prep.
contact-importer
Bulk create or update person notes from Slack profiles. Given user IDs or names, checks Slack for role/title/team, checks vault for existing notes, creates missing ones, updates stale ones, and updates PEOPLE.md index.
wins-capture
Proactively scans for achievements and wins that aren't in the wins doc yet. Checks recent work notes, incident resolutions, git history, and 1:1 feedback for wins-worthy items.
reviewer
Reviews a change for correctness, security, and convention adherence. Use AFTER a resolver edit and BEFORE merge. Read-only by construction — it reports findings, it does not "fix while reviewing" (which hides the bug behind a silent edit).
maintainer
Vault hygiene — index regeneration, link validation, auto-archiving on status change, graph health. Use for "update the index", "fix broken links", "archive resolved blockers".
source-ingestor
Reviews new raw sources, drafts source summaries, extracts candidate concepts, and flags extraction problems.