bar-query

bar-query is a command for coding agents from bar181/bar-observatory. It costs 24 tokens per session (279 once invoked), scanned A, original, MIT.

A read-only query command for BAR Observatory capture databases, which store information recorded from coding-agent sessions.

In plain words
What is it for?
It is for viewing tool usage, session timelines, errors, or selected records through SQL, a language for querying databases.
Why use it?
It answers focused questions that a standard report may not cover without changing the stored data.

Command

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

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

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-query

README.md
[![agentmods](https://agentmods.dev/badge/commands/bar181/bar-observatory/bar-query.svg)](https://agentmods.dev/commands/bar181/bar-observatory/bar-query)
Your own site
<a href="https://agentmods.dev/commands/bar181/bar-observatory/bar-query"><img src="https://agentmods.dev/badge/commands/bar181/bar-observatory/bar-query.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 279 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 $0.00024 $0.00279
Opus 5 $0.00012 $0.00139
Sonnet 5 $0.00005 $0.00056
Haiku 4.5 $0.00002 $0.00028

Measured 5d ago against content hash b89114e2d58f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bar-query 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.

commands/bar-query.md · 21 lines

What it actually says

$ARGUMENTS

Answer a specific question about a session that the pre-built report doesn't cover, using BAR Observatory's direct read-only query surface.

  1. Determine the database path, defaulting to .bar/ambient.sqlite.
  2. Parse $ARGUMENTS for intent:
    • "what tools" / "tool usage" → bar query <db> tools
    • "timeline" / "what happened" / "in order" → bar query <db> timeline
    • "errors" / "what failed" / "silent failures" → bar query <db> errors
    • anything else that needs a specific slice → bar query <db> --sql "SELECT ..." (the connection is opened read-only; a write statement is refused by SQLite itself, not a filter you need to enforce yourself)
  3. Add --format json if the result is for you to parse, --format table if it's for the user to read directly. --limit N windows the output (--limit 0 = all rows).
  4. Run bar query <db> --list first if you're unsure what's available.
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 · 21 lines · 24 tokens per session scan A b89114e2d58f

Subscribe to this mod's changes

bar-query is a command published in the GitHub repository bar181/bar-observatory (22 stars, last pushed 8d ago), licensed MIT. It adds 24 tokens to every session and 279 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.

Related

Other commands, from other repositories

sync

Sync the audit manifest with Azure DevOps work items — set the connector up for the first time (connect: verify the transport, report which auth path is in effect, prove access read-only, detect the board's process), push manifest bugs/tasks/phases to ADO (board states, sprint stamp, Remaining Work, comments), pull…

AleksandarBisevac/claude-plugins · 100 tokens

init

Multi-agent codebase audit that GENERATES the audit manifest (phases/tasks) at manifestPath. Interviews you for scope/goals, fans out parallel read-only explorers, synthesizes findings, then presents the proposed phases for approval BEFORE writing — approve to materialize, or park them as proposals for later…

AleksandarBisevac/claude-plugins · 92 tokens

task

Add a tracked task to the audit manifest — every answer is a flag, and the dialogue only covers what the caller did not pass — move one between phases, or cancel work that will not be done. add allocates the id, initializes all orchestrator fields, updates fileIndex, and revalidates; move renumbers a task into another…

AleksandarBisevac/claude-plugins · 149 tokens

panel

Audit pipeline: open / stop / check a local control-panel UI to visually manage .claude/audit.config.json and the manifest's composition levers (reviewSkill, per-task skills/models, buildCommands) — with live validation and discovery of the skills & agents available in this repo + globally. Ephemeral, on-demand; a…

AleksandarBisevac/claude-plugins · 79 tokens

status

Audit pipeline: print manifest status — phases, tasks, bugs, the ready-now list and what each pending task is waiting on; or, with --gate, turn that same state into a CI pass/fail verdict over conditions you pick with --fail-on. Read-only, no locks, no mutations.

AleksandarBisevac/claude-plugins · 61 tokens

doctor

Audit pipeline: diagnose the setup before it bites — interpreter the hooks will use, git root, config, manifest + shard integrity, which plan-gate tier is active, submodule conflicts, build runners, whether the skills the plan names would resolve from a clone or only here, whether hooks have ever fired and which copy…

AleksandarBisevac/claude-plugins · 108 tokens