triage-beads

triage-beads is a skill for Claude Code, Codex from jtsternberg/claude-plugins. It costs 186 tokens per session (2,741 once invoked), scanned A, original, MIT.

A tool for reviewing every open Beads task, where Beads is a system for tracking small development tasks and their dependencies. It checks each task against the current repository and classifies its real status.

In plain words
What is it for?
Reconcile open, in-progress, and blocked tasks using git history, tests, tool versions, and blockers, with an optional report-only mode.
Why use it?
It prevents old, completed, or externally blocked tasks from making the backlog misleading. It can close tasks that are already satisfied and park tasks that cannot currently move forward.

Skill for Claude CodeCodex

Written for Claude Code and Codex: argument-hint in frontmatter, but also agents/openai.yaml present. Also seen: mentions Claude Code; mentions Codex.

Part of the beads-workflow plugin — 4 skills shipped together

Good fit Reconcile open, in-progress, and blocked tasks using git history, tests, tool versions, and blockers, with an optional report-only mode.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jtsternberg/claude-plugins/triage-beads
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.

Any agent
npx skills add jtsternberg/claude-plugins --skill triage-beads
Clone the repo
git clone --depth 1 https://github.com/jtsternberg/claude-plugins

Made for: Claude Code, Codex.

Or install beads-workflow, the plugin that ships this one along with the rest of its 4 skills.

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 triage-beads

README.md
[![agentmods](https://agentmods.dev/badge/skills/jtsternberg/claude-plugins/triage-beads/github.svg)](https://agentmods.dev/skills/jtsternberg/claude-plugins/triage-beads)
Your own site
<a href="https://agentmods.dev/skills/jtsternberg/claude-plugins/triage-beads"><img src="https://agentmods.dev/badge/skills/jtsternberg/claude-plugins/triage-beads/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 triage-beads

Your own site · 80×15
<a href="https://agentmods.dev/skills/jtsternberg/claude-plugins/triage-beads"><img src="https://agentmods.dev/badge/skills/jtsternberg/claude-plugins/triage-beads.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 186 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,741 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 $0.00186 $0.02741
Opus 5 $0.00093 $0.01371
Sonnet 5 $0.00037 $0.00548
Haiku 4.5 $0.00019 $0.00274

Measured 9d ago against content hash 7524f2a946ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

triage-beads 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/collect-open-beads.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/beads-workflow/skills/triage-beads/SKILL.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Triage Beads

Sweep every open bead and do the triage a careful engineer does by hand: figure out which are secretly already done, which are stuck on something you can't provide, and which genuinely need JT. JT's complaint is that beads pile up and rot — this skill exists to keep the backlog honest without asking him to grind through the whole list one at a time.

Optional flags: $ARGUMENTS

Codex: if the invocation text above is not populated, use the text after the skill name. If none is available, run with no flags (full sweep, writes enabled). The bundled-script path shown below resolves under Claude Code; wherever it appears, substitute the directory containing this SKILL.md.

Parse the flags:

  • --dry-run — reconcile and classify everything, print the full report, but make zero writes (no closes, no comments). Use this for the first run in an unfamiliar repo, or any time JT wants to preview the plan before acting.
  • --status <list> — override which statuses to sweep (default open,in_progress,blocked). Comma-separated.
  • --label <label> — scope the sweep to one label.

The one rule everything else serves

Never trust the bead's own text, and never close on assumption. A bead is a claim written in the past. Your job is to check that claim against the repo as it is now. Every close must cite what you actually checked. If you cannot cite evidence, you do not close — you leave it open. This is the difference between triage and vandalism.

Step 1: Build the worklist

Run the collector. It enumerates every non-frozen open bead and — the one piece of bookkeeping worth doing deterministically — resolves each bead's dependencies to their current status, so you get "this bead's blocker has since closed" for free instead of re-deriving it once per open bead.

SKILL_DIR="${CLAUDE_SKILL_DIR}"
bash "$SKILL_DIR/scripts/collect-open-beads.sh" > /tmp/triage-worklist.json

Codex: SKILL_DIR is the directory containing this SKILL.md; substitute it for the token above. Re-assign SKILL_DIR in each block you run — shell state does not persist between them.

Read the full file on GitHub · 217 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 217 lines · 186 tokens per session scan A 7524f2a946ad

Subscribe to this mod's changes

triage-beads is a skill published in the GitHub repository jtsternberg/claude-plugins (5 stars, last pushed 5d ago), licensed MIT. It adds 186 tokens to every session and 2,741 once invoked, about $0.0009 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.

Related

Other skills, from other repositories

systemic-issue-triage

Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.

Gentleman-Programming/gentle-ai · 57 tokens

triage-issue

Intelligently triage bug reports and error messages by searching for duplicates in Jira and offering to create new issues or add comments to existing ones. When an agent needs to: (1) Triage a bug report or error message, (2) Check if an issue is a duplicate, (3) Find similar past issues, (4) Create a new bug ticket…

atlassian/atlassian-mcp-server · 116 tokens

bug-triage

Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.

Donchitos/Claude-Code-Game-Studios · 59 tokens

investigation

Create an investigation ticket + live-doc for sustained root-cause work (retros, bug archaeology, regression hunts).

me2resh/apexyard · 26 tokens

browse-flows

Browse Power Automate environments and flows interactively. Use when the user wants to browse, list, or explore their flows and environments.

microsoft/power-platform-skills · 31 tokens

operating-cadence

Designs the rhythm an organization runs on — which reviews happen weekly, monthly and quarterly, what each one decides, who owns the numbers presented, and how a signal at the front line reaches the people who can act on it. Use this to set up a management operating system, fix a meeting calendar that produces no…

cbrock84/headcount · 95 tokens