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 skills add aiya000/dotfiles --skill nextgit clone --depth 1 https://github.com/aiya000/dotfilesWrote 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.
[](https://agentmods.dev/skills/aiya000/dotfiles/next)<a href="https://agentmods.dev/skills/aiya000/dotfiles/next"><img src="https://agentmods.dev/badge/skills/aiya000/dotfiles/next/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.
<a href="https://agentmods.dev/skills/aiya000/dotfiles/next"><img src="https://agentmods.dev/badge/skills/aiya000/dotfiles/next.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00057 | $0.01127 |
| Opus 5.5 | $0.00023 | $0.00451 |
| Sonnet 5.5 | $0.00011 | $0.00225 |
| Haiku 4.5 | $0.00006 | $0.00113 |
Grade A, and why
next 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
next
Recover from a stalled turn and correctly continue the work the assistant was about to perform.
When to use
Use this skill when the previous assistant turn failed to make progress, typically because:
- The response ended with prose that described a tool call (e.g. stray
<invoke>text, a word likecourse) instead of actually invoking a tool - A tool call was malformed or incomplete, so nothing executed and the turn appears "stopped"
- The assistant narrated an intended next action but never carried it out
- The user reports the assistant is stuck with phrases like "止まってる", "止まってるよ", "stopped", "why did it stop", "続けて", or invokes
/next
This skill is not only user-invoked. Trigger it autonomously whenever the stall pattern above is detected — at the start of a turn (looking back at the previous turn) or before ending a turn (self-check). See "Autonomous self-detection" below.
Root cause reminder
The most common cause is a broken tool call: the assistant wrote the text of a tool invocation into the message body without emitting a real, well-formed tool call. The turn then ends with no side effects, looking frozen to the user.
The fix is not to re-explain — it is to actually execute the intended action with a correct tool call.
Autonomous self-detection (no /next needed)
Do not wait for the user to invoke /next or say "止まってる". Detect the stall yourself and recover automatically.
- Before ending any turn, self-check: did I actually emit real tool calls for every action I described, or did I write tool-call text (
<invoke>,<parameter>, stray marker words likecourse) into prose? If any intended action did not run, do not end the turn — execute it now with a real tool call. - At the start of every turn, look back one step: if the previous assistant turn narrated an action or contained tool-call fragments but produced no matching tool result, treat this exact situation as an implicit
/nextand run this skill's Behavior immediately, without being asked. - Recurrence rule: the moment the same stall pattern appears again, self-trigger this skill. Never rely on the user to notice and re-invoke it.
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 · 80 lines · 57 tokens per session scan A beb7d4917b46
next is a skill published in the GitHub repository aiya000/dotfiles (21 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 1,127 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 2026-09-15.
Other skills, from other repositories
restart__pull_request
A pull-request restart workflow for replacing a messy review with a new pull request containing one clean commit and a summary of the earlier discussion.
rescue__pull_request_review
An automated workflow for handling GitHub pull-request review comments, applying requested code changes, committing them, and pushing them back.
submit__pull_request
An automated pull-request submission workflow. A pull request is a request for a code change to be reviewed and merged; this workflow writes its explanation, creates it, watches its automated checks, and fixes failed checks.
write__pull_request
A workflow for writing a pull request description, the explanation attached to a proposed code change for review. It analyses the changes and commit history.
monitor__ci_status
An automated monitor for GitHub Actions, the service that runs checks such as tests after code changes. It watches all checks after a pull request or a push to a pull-request branch and can invoke a failure-recovery process.
monitor__pull_request_conflict
An automated check for GitHub pull requests, which are proposed code changes awaiting review or merging.