A read-only status report for an .aiwork task folder, showing completed work, pending human decisions, blockers, verification, and the next action.

Use it to check the state of a specification, plan, or ticket folder and identify which ready ticket or action should come next.

It gathers status from task plans, tickets, reviews, and implementation notes instead of making you inspect each file yourself. It does not change the task.

next-steps — Skill for Claude Code by lttr/claude-marketplace

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 lttr/claude-marketplace --skill next-steps

Clone the repo

git clone --depth 1 https://github.com/lttr/claude-marketplace

Made for: Claude Code.

Or install aiwork, the plugin that ships this one along with the rest of its 12 skills, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/lttr/claude-marketplace/next-steps/github.svg)](https://agentmods.dev/skills/lttr/claude-marketplace/next-steps)

Your own site

<a href="https://agentmods.dev/skills/lttr/claude-marketplace/next-steps"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/next-steps/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/lttr/claude-marketplace/next-steps"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/next-steps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 899 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.

Model	Per session	Once invoked
Fable 5.1	$0.00050	$0.00899
Opus 5.5	$0.00020	$0.00360
Sonnet 5.5	$0.00010	$0.00180
Haiku 4.5	$0.00005	$0.00090

Measured 1mo ago against content hash 5fbdd3d5270f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

next-steps 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 1mo 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.

plugins/aiwork/skills/next-steps/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Next Steps

Read-only status report for one .aiwork/ task folder. Follows the aiwork-protocol skill; changes nothing.

1. Resolve input

$ARGUMENTS is a spec, plan, ticket, or task folder path. A file path resolves to its task folder (a ticket's is the folder above tickets/). With no args, find the most recently modified task folder per aiwork-protocol conventions. Nothing found → say so and stop.

2. Gather

Read frontmatter first, prose only where needed.

intent.md: status (proposed / accepted / declined).
spec.md (or the current plan*.md when there is no spec, skipping any with superseded_by): status, blocked_by, verified. Note whether the spec still has open questions, TBDs, or a non-empty Open Concerns section.
tickets/, if present: for each ticket its number, title, status (ready / in-progress / done), blocked_by, verified, and the count of ticked vs unticked acceptance criteria. The frontier is every ready ticket whose blockers are all done.
review*.md: present or not, and its reviewed_sha.
implementation-notes*.md: any entries the human must act on.

Read the vocabulary as the protocol defines it:

Ticket folders carry the truth in ticket statuses; the spec's own status is optional there.
Without tickets, an absent spec status means unknown, not not-started.
agent-done means the agent finished and handed over; report it as awaiting the human's check, never as finished. done on a spec is the human's call.
Older folders may use draft / active / complete / superseded; map them to the nearest current value and say so.

3. Report

Brief. Print, in order:

Headline: task folder, then one line — intent status, spec status (or "tickets: N done / M in progress / K ready / J blocked").
Tickets table when tickets/ exists: number, title, status, blockers, criteria ticked, verified passes. Skip the table for folders without tickets.
Next action, exactly one line, first match wins:
- intent not accepted → decide the intent (/aiwork:to-spec waits on it)
- no spec and no tickets → /aiwork:to-spec
- spec with open questions / Open Concerns → resolve them; /aiwork:implement-spec stops on them
- spec, no tickets, not small → /aiwork:to-tickets; small → /aiwork:implement <spec>
- frontier non-empty → /aiwork:implement-spec, or /aiwork:implement tickets/<NN> naming the first frontier ticket
- a ticket in-progress → resume it
- all tickets done, no review*.md → /aiwork:implement-spec runs the wrap-up review
- spec agent-done → the human exercises the feature and reads the code, then sets done
- spec done → all done
- spec blocked or every remaining ticket blocked → name the blocker
Needs a human: only if any exist — blocked_by causes, unresolved implementation notes, done tickets with unticked criteria or without an on-app verified pass (behaviour / ux / human), a review whose reviewed_sha is missing.

Read the full file on GitHub · 52 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.

1mo ago First seen · 52 lines · 50 tokens per session scan A 5fbdd3d5270f

Subscribe to this mod's changes

next-steps is a skill published in the GitHub repository lttr/claude-marketplace (2 stars, last pushed 14d ago), licensed MIT. It adds 50 tokens to every session and 899 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-12.

Claude Code Planning Project management claude-ai workflow

next-steps

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Next Steps

1. Resolve input

2. Gather

3. Report

What this file has done since we first saw it

Other skills, from other repositories

issue-triage

multi-agent

tencent-meeting-mcp

flow-next-flow

flow-next-plan

project-execution