obsidian-mind: Agent for Claude Code

.claude/agents/review-fact-checker.md

review-fact-checker is an agent for Claude Code from breferrari/obsidian-mind. It costs 27 tokens per session (499 once invoked), scanned A, original, MIT.

An agent that checks every factual claim in a review draft against sources stored in a knowledge vault. It labels claims as verified, unverified, or flagged when evidence is missing or conflicts.

In plain words
What is it for?
Use it to fact-check a review draft against performance records, project notes, people notes, and other vault sources.
Why use it?
It reduces unsupported numbers, timelines, attributions, comparisons, and personal claims in self-reviews or peer reviews. It shows which statements need evidence or correction.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is breferrari/obsidian-mind's own configuration. It tells Claude Code how to work on obsidian-mind itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything obsidian-mind configures →

Part of the obsidian plugin — 8 skills, 20 commands, 10 agents, 5 hooks, 1 MCP server shipped together

About the project

Obsidian Mind is an Obsidian vault that stores notes, links, indexes, and other accumulated context so AI coding agents can retain memory across sessions. It is designed for Claude Code and also supports Codex CLI and Gemini CLI through shared hooks, commands, and vault data. Its catalogue add-ons package the vault’s commands, agents, skills, hooks, instructions, settings, plugin, and MCP integration.

breferrari/obsidian-mind · 4,631 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to breferrari/obsidian-mind. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/breferrari/obsidian-mind/main/.claude/agents/review-fact-checker.md
Clone the repo
git clone --depth 1 https://github.com/breferrari/obsidian-mind

Made for: Claude Code.

Or install obsidian, the plugin that ships this one along with the rest of its 8 skills, 20 commands, 10 agents, 5 hooks, 1 MCP server.

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 review-fact-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/breferrari/obsidian-mind/review-fact-checker/github.svg)](https://agentmods.dev/agents/breferrari/obsidian-mind/review-fact-checker)
Your own site
<a href="https://agentmods.dev/agents/breferrari/obsidian-mind/review-fact-checker"><img src="https://agentmods.dev/badge/agents/breferrari/obsidian-mind/review-fact-checker/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for review-fact-checker

Your own site · 80×15
<a href="https://agentmods.dev/agents/breferrari/obsidian-mind/review-fact-checker"><img src="https://agentmods.dev/badge/agents/breferrari/obsidian-mind/review-fact-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 499 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00027 $0.00499
Opus 5 $0.00014 $0.00249
Sonnet 5 $0.00005 $0.00100
Haiku 4.5 $0.00003 $0.00050

Measured 12d ago against content hash a386aada6431, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

review-fact-checker 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 12d 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.

.claude/agents/review-fact-checker.md · 62 lines

What it actually says

Review Fact-Checker

Takes a review draft file (self-review or peer review) and systematically verifies every factual claim against vault sources.

Input

The user provides a file path to a review draft.

Process

  1. Read the draft file completely.

  2. Extract every factual claim. A claim is:

    • A number (PR count, days, team size, percentage)
    • A timeline (dates, sequences, "before X happened")
    • An attribution ("she authored", "he initiated", "I led")
    • A comparison ("first time", "only", "every", "never")
    • A characterization ("self-initiated", "without being asked", "autonomously")
    • A day-of-week implication ("weekend", "same day", "overnight")
  3. For each claim, search the vault:

    • perf/evidence/ for PR data
    • perf/<cycle>/ for review briefs
    • perf/brag/ for quarterly brag notes
    • perf/competencies/ for competency criteria
    • work/ for project notes
    • org/people/ for person notes
    • brain/ for operational context
  4. Classify each claim:

    • Verified: Found in vault with matching source
    • Unverified: Not found in vault, but plausible (from brag sheet, conversation)
    • Flagged: Contradicts vault evidence, embellished, or could be challenged
    • Date check: Any day-of-week claim — verify with date command
  5. For flagged claims, suggest a fix.

Output

Return a structured report:

## Verified (X claims)
- [claim] — source: [file]

## Unverified (X claims)
- [claim] — no vault source, from [brag sheet / conversation / inference]

## Flagged (X claims)
- [claim] — issue: [what's wrong] — fix: [suggestion]
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. 12d ago First seen · 62 lines · 27 tokens per session scan A a386aada6431

Subscribe to this mod's changes

review-fact-checker is an agent published in the GitHub repository breferrari/obsidian-mind (4,631 stars, last pushed 9d ago), licensed MIT. It adds 27 tokens to every session and 499 once invoked, about $0.0001 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.