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.
git clone --depth 1 https://github.com/ProjectDXAI/labratWrote 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/commands/projectdxai/labrat/frame-break)<a href="https://agentmods.dev/commands/projectdxai/labrat/frame-break"><img src="https://agentmods.dev/badge/commands/projectdxai/labrat/frame-break/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/commands/projectdxai/labrat/frame-break"><img src="https://agentmods.dev/badge/commands/projectdxai/labrat/frame-break.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 | $0.00000 | $0.00160 |
| Opus 5.5 | $0.00000 | $0.00064 |
| Sonnet 5.5 | $0.00000 | $0.00032 |
| Haiku 4.5 | $0.00000 | $0.00016 |
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 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.
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: trueandremaining_cheap_probes: 0across families. If either condition is false, stop and run/why-stuckinstead. - 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 tologs/expansions/<timestamp>.mdas theexpansion_scoutexpects. - Do not edit
branches.yamldirectly. Let the expansion_scout flow merge 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 · 8 lines · 0 tokens per session scan A 25f4d8eaefa8
frame-break is a command published in the GitHub repository ProjectDXAI/labrat (237 stars, last pushed 2mo 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.
Other commands, from other repositories
infogenius
Research-First Image Generation - Facts → Visual Prompt → High-Quality Image.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
close-track
Close a completed track — run quality gate, update conductor state, commit, and optionally handle the git branch.
audit-plugin
Audit plugin skills, commands, and agents for structure, size, and naming issues.
release
Prepare a release (step 1 of 2) — version bump and PR. Cutting the tag is a separate operator-only step.
resume
Auto-detect and resume any interrupted Plan Cascade task. Detects mega-plan, hybrid-worktree, or hybrid-auto context and routes to the appropriate resume command.