A controlled method for changing an agent's approach when its current lines of investigation are no longer useful. A frame break means proposing a new branch or way to organize the search.

Use it when cheap probes and audits are finished, the state requires a frame break, and the current families of approaches cannot express the problem.

It prevents the agent from changing strategy too early, before simpler checks are exhausted. It records the proposed change for a later review process instead of applying it directly.

frame-break — Command for Claude Code by ProjectDXAI: A controlled method for changing an agent's approach when…

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.

agentmods

npx agentmods add commands/projectdxai/labrat/frame-break

Clone the repo

git clone --depth 1 https://github.com/ProjectDXAI/labrat

Made for: Claude Code.

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/commands/projectdxai/labrat/frame-break.svg)](https://agentmods.dev/commands/projectdxai/labrat/frame-break)

Your own site

<a href="https://agentmods.dev/commands/projectdxai/labrat/frame-break"><img src="https://agentmods.dev/badge/commands/projectdxai/labrat/frame-break.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 160 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00160
Opus 5	$0.00000	$0.00080
Sonnet 5	$0.00000	$0.00032
Haiku 4.5	$0.00000	$0.00016

Measured 4d ago against content hash 25f4d8eaefa8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frame-break 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 4d 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.

examples/nlp-sentiment/research_lab/.claude/commands/frame-break.md · 8 lines

What it actually says

Trigger a frame-break cycle only after cheap probes and audits are no longer productive.

Confirm state/frontier.json.frame_break_required: true and remaining_cheap_probes: 0 across families. If either condition is false, stop and run /why-stuck instead.
Read frame_break.md.
Read the last ten entries in state/evaluations.jsonl. Look for structural patterns that the current families cannot express.
Propose a patch to branches.yaml, a new family or a revised axis set, and write it to logs/expansions/<timestamp>.md as the expansion_scout expects.
Do not edit branches.yaml directly. Let the expansion_scout flow merge it.

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.

4d ago First seen · 8 lines · 0 tokens per session scan A 25f4d8eaefa8

Subscribe to this mod's changes

frame-break is a command published in the GitHub repository ProjectDXAI/labrat (239 stars, last pushed 27d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 160 tokens. 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 2026-08-30.

Multi-Agent ai-agents autonomous-research claude-code experiment-management research-automation

riskreview

The user invoked the /riskreview facade command from the risk-review-pipeline pack.

inclusionAI/Avernet · 11 tokens

triage

Triage review findings one by one — present pending TODOs for user decision (approve, skip, modify).

JairoTorregrosa/jaiskills · 25 tokens

audit-plugin

Audit plugin skills, commands, and agents for structure, size, and naming issues.

justinjdev/fellowship · 17 tokens

youtube-pulse

Summarize latest videos from tracked YouTube channels and extract short-term investment signals relevant to current holdings. Run after /market-pulse for context, or standalone for a quick opinion check.

haiiibin/claude-multi-agent-investing · 38 tokens

mega-plan

Generate a mega-plan for project-level multi-feature orchestration. Breaks a complex project into parallel features with dependencies. Usage: /plan-cascade:mega-plan [--flow ] [--tdd ] [--confirm] [--no-confirm] [--spec ] [--first-principles] [--max-questions N] [design-doc-path].

Taoidle/plan-cascade · 95 tokens

pm-board

Open the great-pm board — a native, zero-dependency project board (hybrid stage×status Kanban + artifact panels + verdict metrics) served from the great-pm plugin itself. Self-contained, no npm packages.

VandanaAjayDubey111/great-pm · 46 tokens