bar-doctor

bar-doctor is a command for Claude Code from bar181/bar-observatory. It costs 22 tokens per session (177 once invoked), scanned A, original, MIT.

A live health-check command for BAR Observatory, which records information about coding-agent sessions.

In plain words
What is it for?
It is for checking the BAR recorder, reviewing passed and warning checks, and finding out what kinds of session data were captured.
Why use it?
It shows whether recording is working now and which capture channels actually contain data, rather than assuming the setup succeeded.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the bar-observatory plugin — 5 commands, 21 hooks shipped together

Good fit It is for checking the BAR recorder, reviewing passed and warning checks, and finding out what kinds of session data were captured.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/bar181/bar-observatory/bar-doctor
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.

Clone the repo
git clone --depth 1 https://github.com/bar181/bar-observatory

Made for: Claude Code.

Or install bar-observatory, the plugin that ships this one along with the rest of its 5 commands, 21 hooks.

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 bar-doctor

README.md
[![agentmods](https://agentmods.dev/badge/commands/bar181/bar-observatory/bar-doctor/github.svg)](https://agentmods.dev/commands/bar181/bar-observatory/bar-doctor)
Your own site
<a href="https://agentmods.dev/commands/bar181/bar-observatory/bar-doctor"><img src="https://agentmods.dev/badge/commands/bar181/bar-observatory/bar-doctor/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 bar-doctor

Your own site · 80×15
<a href="https://agentmods.dev/commands/bar181/bar-observatory/bar-doctor"><img src="https://agentmods.dev/badge/commands/bar181/bar-observatory/bar-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 177 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 $0.00022 $0.00177
Opus 5 $0.00011 $0.00088
Sonnet 5 $0.00004 $0.00035
Haiku 4.5 $0.00002 $0.00018

Measured 9d ago against content hash 7dc9a119853f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

bar-doctor 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 9d 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.

commands/bar-doctor.md · 17 lines

What it actually says

$ARGUMENTS

Run BAR Observatory's live diagnostic — distinct from the deterministic report, this answers "is the recorder healthy right now?" not "what happened in this session?"

  1. Determine the database path from $ARGUMENTS, defaulting to .bar/ambient.sqlite. If no database has been initialized yet, run bar doctor with no argument — it still reports on the bar binary itself.
  2. Run: bar doctor <db>
  3. Summarize the result plainly: which checks passed, which warned, and — critically — which capture channels actually have rows versus which are honestly reported as not recorded. Never round a warning up to "everything's fine."
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. 9d ago First seen · 17 lines · 22 tokens per session scan A 7dc9a119853f

Subscribe to this mod's changes

bar-doctor is a command published in the GitHub repository bar181/bar-observatory (22 stars, last pushed 12d ago), licensed MIT. It adds 22 tokens to every session and 177 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.