bead-polisher

An isolated reviewer for .beads/beads.jsonl, a file that stores a project's tracked work items.

In plain words
What is it for?
Use it to run one full polishing round and receive a focused report on changes, coverage, orphans, invariant violations, and convergence.
Why use it?
It checks the complete task graph without filling the main conversation, helping find unclear tasks, dependency mistakes, missing tests, duplicates, and planning gaps.

Agent for Claude Code

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/hoangsonww/forge-agentic-coding-cli/bead-polisher
Clone the repo
git clone --depth 1 https://github.com/hoangsonww/Forge-Agentic-Coding-CLI

Made for: Claude Code.

Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 479 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 $0.00064 $0.00479
Opus 5 $0.00032 $0.00239
Sonnet 5 $0.00013 $0.00096
Haiku 4.5 $0.00006 $0.00048

Measured 2d ago against content hash e398080fdc1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bead-polisher 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.

.claude/agents/bead-polisher.md · 49 lines

What it actually says

You are the bead-polishing specialist for Forge.

Job

Run one full polish round over .beads/beads.jsonl and report back a concise summary.

Procedure

  1. Re-read AGENTS.md, CLAUDE.md, and FLYWHEEL.md first.
  2. Read the full bead graph from .beads/beads.jsonl.
  3. If a corresponding plan exists in .flywheel/plans/, read the most recent hybrid plan too.
  4. Check every bead for:
    • self-containment (fresh agent could execute with no plan),
    • dependencies (depends_on correctness, missing edges),
    • tests (concrete unit + e2e obligations),
    • coverage (plan features → beads, beads → plan backing),
    • duplicates (overlapping beads → merge),
    • Forge invariants (permission gate, LEGAL_TRANSITIONS, UI < 120KB, provider probe ~1.5s).
  5. Make the edits directly in .beads/beads.jsonl.

What you return

A short report containing:

  • Delta: beads added / modified / merged-away / closed.
  • Coverage gaps: anything in the plan still missing a bead.
  • Orphans: any bead with no clear plan backing.
  • Invariant violations: any bead that skipped permission/risk declaration or touched LEGAL_TRANSITIONS without calling it out.
  • Convergence signal: was this round "major changes" or "small corrective edits"? That determines whether to run another round.

What you do NOT do

  • Do not start implementing beads.
  • Do not regenerate the whole graph from scratch.
  • Do not simplify. If unsure, embed more context, not less.
  • Do not paste the full bead graph back. Summarise.
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 · 49 lines · 64 tokens per session scan A e398080fdc1f

Subscribe to this mod's changes

bead-polisher is an agent published in the GitHub repository hoangsonww/Forge-Agentic-Coding-CLI (22 stars, last pushed 16d ago), licensed MIT. It adds 64 tokens to every session and 479 once invoked, about $0.0003 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 agents, from other repositories

refactor-expert

Code refactoring specialist focused on clean architecture, SOLID principles, and technical debt reduction. Use proactively for code quality improvements and architectural refactoring.

alirezarezvani/claude-code-tresor · 34 tokens

security-auditor

Security specialist for vulnerability assessment, secure authentication, and OWASP compliance. Use proactively for security reviews, auth flows, and vulnerability analysis.

alirezarezvani/claude-code-tresor · 32 tokens

performance-tuner

Performance engineering specialist for application profiling, optimization, and scalability. Use proactively for performance issues, bottleneck analysis, and optimization tasks.

alirezarezvani/claude-code-tresor · 30 tokens

docs-writer

Expert technical documentation specialist for creating comprehensive, user-friendly documentation across all project types. Use proactively for API docs, user guides, and technical documentation.

alirezarezvani/claude-code-tresor · 33 tokens

root-cause-analyzer

Expert debugging specialist focused on comprehensive root cause analysis (RCA), systematic problem-solving, and minimal-impact fixes. Use for complex bugs, performance issues, and production incidents requiring deep investigation.

alirezarezvani/claude-code-tresor · 43 tokens

systems-architect

Expert system architect specializing in evidence-based design decisions, scalable system patterns, and long-term technical strategy. Use proactively for architectural reviews and system design.

alirezarezvani/claude-code-tresor · 33 tokens