next

next is a command for Claude Code from AleksandarBisevac/claude-plugins. It costs 32 tokens per session (517 once invoked), scanned A, original, MIT.

A command that executes the next ready task in a code-audit pipeline. It follows the plan's phase and task order, can preview the next action without changing anything, and reports what is ready afterward.

In plain words
What is it for?
Use it to advance an existing audit plan one task at a time. Use preview mode to see what would run before making changes, or normal mode to execute the next eligible task.
Why use it?
Multi-step audits become difficult to coordinate when tasks depend on one another or some can safely run in parallel. This command applies the plan's readiness rules and keeps progress visible.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the audit plugin — 2 skills, 20 commands, 4 agents, 4 hooks shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add AleksandarBisevac/claude-plugins
Claude Code
/plugin install audit

Made for: Claude Code.

Or install audit, the plugin that ships this one along with the rest of its 2 skills, 20 commands, 4 agents, 4 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 next

README.md
[![agentmods](https://agentmods.dev/badge/commands/aleksandarbisevac/claude-plugins/next.svg)](https://agentmods.dev/commands/aleksandarbisevac/claude-plugins/next)
Your own site
<a href="https://agentmods.dev/commands/aleksandarbisevac/claude-plugins/next"><img src="https://agentmods.dev/badge/commands/aleksandarbisevac/claude-plugins/next.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 517 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.00517
Opus 5 $0.00016 $0.00259
Sonnet 5 $0.00006 $0.00103
Haiku 4.5 $0.00003 $0.00052

Measured 6d ago against content hash 3056c9a737c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 6d 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/audit/commands/next.md · 36 lines

What it actually says

/audit:next — execute the next ready task

Read ${CLAUDE_PLUGIN_ROOT}/reference/orchestrator.md and ${CLAUDE_PLUGIN_ROOT}/reference/manifest-conventions.md first.

If $ARGUMENTS contains --dry-run: follow the orchestrator's Dry-run / preview section — show the next ready task and what would run, and STOP without mutating.

Otherwise run the full preflight (steps 1–5, including acquiring the lock) and emit Progress output.

  1. Print the entry view first, verbatim: python3 "${CLAUDE_PLUGIN_ROOT}/scripts/status/audit-status.py" <manifestPath> — it names every ready task, in order, with what the rest are waiting on. Do not re-tabulate it and do not re-derive the readiness rule by hand; the first entry under READY NOW is the task this command runs.
  2. Find the first ready task (phase order, then task-id order) per the Readiness rule.
  3. If none is ready: the entry view's waiting on column already says why, per task — relay it rather than restating it. Release the lock and stop.
  4. Otherwise run Execute the task (orchestrator), then follow Reporting — outcome + what is ready next. Release the lock.

Before that release, if the task did not reach done: the record of its gate has nothing to ride out on. This command commits on success and only on success, so a run ending blocked — or stopping on the infrastructure path — leaves the rows the gate just wrote sitting in the working tree with nothing coming behind them to carry them. ${CLAUDE_PLUGIN_ROOT}/commands/run.mdWhat one run leaves behind states it in full: which invocation becomes evidence, why a refused pointer is not a failure, and what commit-audit-state.py may and may not stage. It applies here unchanged — the two commands differ in how the task is chosen and in nothing else.

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. 6d ago First seen · 36 lines · 32 tokens per session scan A 3056c9a737c9

Subscribe to this mod's changes

next is a command published in the GitHub repository AleksandarBisevac/claude-plugins (4 stars, last pushed 5d ago), licensed MIT. It adds 32 tokens to every session and 517 once invoked, about $0.0002 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.