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.
npx agentmods add skills/kelp/agent-plugins/next-todonpx skills add kelp/agent-plugins --skill next-todogit clone --depth 1 https://github.com/kelp/agent-pluginsWhat 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 | $0.00101 | $0.03194 |
| Opus 5 | $0.00051 | $0.01597 |
| Sonnet 5 | $0.00020 | $0.00639 |
| Haiku 4.5 | $0.00010 | $0.00319 |
Grade A, and why
next-todo 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.
How it starts
The opening of the file, as written. The whole thing — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/next-todo
Do this whole procedure for one slice. Do not skip the plan review. Do not skip the comment drain. Do not start a second slice in the same change.
The project's CLAUDE.md is the architecture contract. This skill is the operating procedure. If this skill conflicts with that file or the Rules binding, follow those files.
Input
Slice: $ARGUMENTS
- Empty → pick the next slice from the backlog binding.
- A heading → that heading is the slice, if its
predecessors are already on
main.
Binding
Read ## Next TODO binding in the project's CLAUDE.md.
If that heading is missing, stop and tell the user to
run /next-todo-init first.
Every value marked (binding) below comes from that section:
- Backlog — file, how to pick the next slice, what one slice is.
- Plan — where the plan artifact lives.
- Spec — spec file(s) and the approval rule.
- Gates — local commands before each commit.
- CI — required checks the parent waits on.
- Review axes — replacements for the defaults below, if any.
- Rules — TDD, style, and dependency files.
When to use
Use this skill when the user asks to land a slice, do the next TODO item, plan a slice, or drain PR review comments to all-clear.
Do not use this skill for work that is not a backlog slice, unless the user maps that work onto a named slice. Do the user's requested work instead.
1. Choose the work
- Open the backlog (binding) the way that binding says. Do not read the rest of that file.
- Fetch
origin/mainwhen the local default branch may be stale. - Confirm the local
mainmatchesorigin/mainbefore you branch. - If the user named a slice, take that heading. Stop if a predecessor is still open.
- Otherwise take the next slice the binding names. Stop if a predecessor is still open.
- Record the exact heading. That heading is the slice name. One heading is one pull request.
Do not combine slices. Do not pull in the next heading "while you are here." After you land the slice, update the backlog pointer the way the binding says.
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.
- 2d ago First seen · 369 lines · 101 tokens per session scan A 270357062317
next-todo is a skill published in the GitHub repository kelp/agent-plugins (2 stars, last pushed 9d ago), licensed MIT. It adds 101 tokens to every session and 3,194 once invoked, about $0.0005 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.
Other skills, from other repositories
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
sprint-plan
Plan a sprint with capacity estimation, story selection, dependency mapping, and risk identification. Use when preparing for sprint planning, estimating team capacity, selecting stories, or balancing sprint scope against velocity.
job-stories
Create job stories using the 'When [situation], I want to [motivation], so I can [outcome]' format with detailed acceptance criteria. Use when writing job stories, creating JTBD-style backlog items, or expressing user situations and motivations.
user-stories
Create user stories following the 3 C's (Card, Conversation, Confirmation) and INVEST criteria with descriptions, design links, and acceptance criteria. Use when writing user stories, breaking down features into backlog items, or defining acceptance criteria.
wwas
Create product backlog items in Why-What-Acceptance format — independent, valuable, testable items with strategic context. Use when writing structured backlog items, breaking features into work items, or using the WWA format.