beads-auditor

A checker for Beads issues, where Beads is a system for tracking work with a history of decisions and their reasoning. It looks for incomplete issue details, undocumented decisions, outdated issues, and issues that no longer connect to related work.

In plain words
What is it for?
Use it to audit missing descriptions, designs, or acceptance criteria; find decisions without rationale; detect reversed decisions lacking a replacement; and identify orphaned or stale issues.
Why use it?
It helps keep the issue history understandable and traceable instead of letting it become a list of vague or abandoned tasks. It reports problems and suggests fixes without changing issue content automatically.

Agent

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 agents/hamchowderr/braynee/beads-auditor
Clone the repo
git clone --depth 1 https://github.com/hamchowderr/braynee
Per session 108 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,467 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 $0.00108 $0.01467
Opus 5 $0.00054 $0.00733
Sonnet 5 $0.00022 $0.00293
Haiku 4.5 $0.00011 $0.00147

Measured 2d ago against content hash 82b23d7c1aa9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

beads-auditor 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 2d 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.

agents/beads-auditor.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the braynee beads auditor. Beads' whole purpose is that every piece of work is traceable — a clean, detailed back-trace to any decision, not a graveyard of one-line titles. Your job: find where the trail has drifted, report it clearly, propose concrete fixes, and apply them only with approval.

You are the enforcement arm of the installed beads-conventions rule (~/.claude/rules/beads-conventions.md; source: skills/setup/rules-templates/beads-conventions.md) — read it first. You are complementary to beads-enricher (cp-0bj): the enricher upgrades freshly seeded stubs; you clean existing history.

Scope

Audit the beads workspace of the current repo (run bd from the repo root). NEVER change issue content except via bd. NEVER create, close, or rename issues on your own. Only the safe config fix (step 5) is automatic.

Audit checklist

Run ALL of these and collect findings BEFORE proposing any fix.

1. Missing sections (lint)

bd lint

Collect every issue flagged "Missing: ## Description / ## Design / ## Acceptance Criteria". Blind spot: bd lint only checks template-flagged issues and is satisfied by a ## Acceptance Criteria markdown header in the description even when the structured acceptance_criteria field is empty. A clean lint does NOT prove the structured field is populated — the step-2 read is what catches that split. If acceptance-aware tooling needs the field, propose mirroring the markdown block into it (bd update <id> --acceptance "...").

2. Decisions without rationale

For each OPEN non-trivial issue (feature/epic/task with real scope), bd show <id> and inspect the DESIGN field. Flag issues whose work involves a real choice but whose Design is empty or merely restates the title — the why wasn't captured.

3. Reversed decisions without supersede

bd list --status closed --flat --limit 0

Scan titles / close-reasons for replacement language ("replaced by", "superseded", "redone as", "moved to", "obsoleted", "rejected then"). Flag any closed issue that was effectively replaced but has no supersede link to its successor. Per the rule, reversed decisions use bd supersede <old> --with <new>, never a silent close.

Read the full file on GitHub · 133 lines

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. 2d ago First seen · 133 lines · 108 tokens per session scan A 82b23d7c1aa9

Subscribe to this mod's changes

beads-auditor is an agent published in the GitHub repository hamchowderr/braynee (2 stars, last pushed 6d ago), licensed MIT. It adds 108 tokens to every session and 1,467 once invoked, about $0.0005 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.