work-status

work-status is a command for Claude Code from MadaraUchiha-314/the-loop. It costs 25 tokens per session (478 once invoked), scanned A, original, MIT.

A read-only status report for a work item, such as a GitHub issue or Jira task, based on its requirements, design, task list, and execution log.

In plain words
What is it for?
Use it to see which planning documents exist, whether they are approved, how many tasks are complete, and what happened most recently.
Why use it?
It shows the current workflow phase and remaining work without changing project files or ticket state.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the the-loop plugin — 2 skills, 16 commands, 2 hooks shipped together

Good fit Use it to see which planning documents exist, whether they are approved, how many tasks are complete, and what happened most recently.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/madarauchiha-314/the-loop/work-status
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.

Clone the repo
git clone --depth 1 https://github.com/MadaraUchiha-314/the-loop

Made for: Claude Code.

Or install the-loop, the plugin that ships this one along with the rest of its 2 skills, 16 commands, 2 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 work-status

README.md
[![agentmods](https://agentmods.dev/badge/commands/madarauchiha-314/the-loop/work-status.svg)](https://agentmods.dev/commands/madarauchiha-314/the-loop/work-status)
Your own site
<a href="https://agentmods.dev/commands/madarauchiha-314/the-loop/work-status"><img src="https://agentmods.dev/badge/commands/madarauchiha-314/the-loop/work-status.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 478 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 $0.00025 $0.00478
Opus 5 $0.00013 $0.00239
Sonnet 5 $0.00005 $0.00096
Haiku 4.5 $0.00003 $0.00048

Measured 7d ago against content hash 1298cc57dd8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

work-status 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 7d 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/work-status.md · 39 lines

What it actually says

the-loop: work-status $ARGUMENTS

Report where a work item stands. Read-only — this command inspects and summarizes; it does not change anything.

Read the the-loop skill and reference/workflow.md for the phase model.

Steps

  1. Locate the spec. Resolve $ARGUMENTS to docs/specs/<id>/. If nothing is found, check for a draft-* folder (pre-ticket) and say so.

  2. Read the artifacts (whichever exist): requirements.md/bugfix.md, design.md, tasks.md, execution-log.md. Also read the ticket's current phase label if the ticketing integration is available. requirements.md and bugfix.md are two accepted names for the same phase-1 artifact — if both are on disk, say so: the requirements-definition gate blocks on it (decision-045).

  3. Summarize:

    • Phase — from the execution log's front-matter and the ticket label (flag any mismatch).
    • Spec status — which of requirements/design/tasks exist and their status (draft / approved) and approvers.
    • Task progress — count of - [x] vs - [ ] in tasks.md (the-loop keeps these current as tasks complete), and which tasks are outstanding.
    • Latest activity — the most recent execution-log entries and any pending review/human action.
    • Next step — the command to move forward (create-design / create-tasks-plan / execute-tasks / finish-tasks).
  4. Present it as a concise, prioritized summary (mermaid where a diagram helps — config.userInteraction). Do not modify any file or ticket.

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. 7d ago First seen · 39 lines · 25 tokens per session scan A 1298cc57dd8b

Subscribe to this mod's changes

work-status is a command published in the GitHub repository MadaraUchiha-314/the-loop (4 stars, last pushed 4d ago), licensed MIT. It adds 25 tokens to every session and 478 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 2026-08-31.