A tool-guided work tracker for managing TODO items in a project. It lets an agent find available work, claim one item, record progress, and finish or release it.

Use it to choose the next task, check its scope, track progress, create work items, review tracker statistics, and manage task priorities.

It keeps work status and ownership in one database instead of relying on hand-edited files or guesses. Claims prevent two workers from taking the same item.

How BenchBox-dev/BenchBox configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to BenchBox-dev/BenchBox. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/BenchBox-dev/BenchBox/develop/.claude/skills/todo-db/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/BenchBox-dev/BenchBox

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/benchbox-dev/benchbox/todo-db.svg)](https://agentmods.dev/skills/benchbox-dev/benchbox/todo-db)

Your own site

<a href="https://agentmods.dev/skills/benchbox-dev/benchbox/todo-db"><img src="https://agentmods.dev/badge/skills/benchbox-dev/benchbox/todo-db.svg" alt="Measured on agentmods" height="20"></a>

Per session 124 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,109 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.

Model	Per session	Once invoked
Fable 5.1	$0.00124	$0.02109
Opus 5	$0.00062	$0.01055
Sonnet 5	$0.00025	$0.00422
Haiku 4.5	$0.00012	$0.00211

Measured yesterday against content hash fee6bc1859ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

todo-db 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 yesterday.

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/skills/todo-db/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

todo-db

The tracker is driven through MCP tool calls, not shell commands. Planning and the working loop exist only as tools; the todo-db CLI keeps a small floor of human and CI verbs listed at the end of this page. If the tools are not available, the MCP server is not registered — see docs/operations/mcp-clients.md in the todo-db repository.

Critical rules

Call get_instructions first in a session. It returns this protocol and, on clients that supply no explicit actor, pins your audit principal.
The loop tools (next, take, context, progress) return a next_action: {"tool": ..., "arguments": {...}}. Follow it rather than guessing. Query and planning tools return their result alone. An idle next returns {"action": "wait", ...} with no tool to call.
One active claim per principal. Taking a second item without releasing or finishing is refused; call claims to see what you hold.
Only the claim holder may progress, finish, or release an item. Keep the claim_token from take; re-read it with context after a restart.
Never hand-edit tracker state, and never create tracker files. The database is the only store.
Do not run the stored verification commands yourself. A human runs them with todo-db verify-run.

The loop

Step	Tool	Notes
1	`next`	Ready queue, or the claim you already hold.
2	`take`	Claim an item. Omit `id` to take the top of the queue.
3	`context`	Bounded context for the claimed item; re-reads `claim_token`.
4	`progress`	One work unit at a time, with real evidence. Refreshes the lease.
5	`finish`	The close gate.
—	`release`	Hand the claim back without finishing.

Reading the response envelope

{"ok": true,  "data": {...}}
{"ok": false, "code": "E_...", "error": "...", "recovery": [...], "kind": "gate|error"}

get_instructions returns markdown text directly; all other query, work, and planning tools return the {ok, ...} JSON envelope.

Read the full file on GitHub · 152 lines

Files

What ships with it

11 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.

yesterday First seen · 152 lines · 124 tokens per session scan A fee6bc1859ea

Subscribe to this mod's changes

todo-db is a skill published in the GitHub repository BenchBox-dev/BenchBox (12 stars, last pushed yesterday), licensed MIT. It adds 124 tokens to every session and 2,109 once invoked, about $0.0006 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 2026-09-05.

Project management

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

story-readiness

Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…

Donchitos/Claude-Code-Game-Studios · 77 tokens

autotask-creator

Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.

Orkas-AI/Orkas · 5 tokens

monorepo-management

Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.

wshobson/agents · 54 tokens

BenchBox: Skill for Claude Code