why-stuck

A diagnostic command for finding out why an automated search process has stopped making progress. The frontier is the current edge of that search: the candidates and directions it can explore next.

In plain words
What is it for?
Use it to inspect recent evaluations, candidate attempts, resource credits, stalled-progress counters, required strategy changes, and pending audits without changing saved state.
Why use it?
It shows which group is blocking progress, what failures are most common, and whether the next action should be an audit, more changes, or a new approach.

Command for Claude Code

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/why-stuck
Clone the repo
git clone --depth 1 https://github.com/ProjectDXAI/labrat

Made for: Claude Code.

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 164 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 $0.00000 $0.00164
Opus 5 $0.00000 $0.00082
Sonnet 5 $0.00000 $0.00033
Haiku 4.5 $0.00000 $0.00016

Measured 3d ago against content hash 6113018ac412, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

why-stuck 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 3d 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/why-stuck.md · 13 lines

What it actually says

Diagnose why the frontier is not moving.

  1. Run python scripts/operator_helper.py status.
  2. Read state/frontier.json, focusing on family_funding credits, plateau_counter, frame_break_required, and audit_queue.
  3. Read the last five entries in state/evaluations.jsonl. Note the distribution of failure_class values.
  4. Read the last five entries in state/candidates.jsonl. Note which families are spending credits without promoting.
  5. Summarize in one paragraph:
    • which family is blocking,
    • what the dominant recent failure class is,
    • whether the next step is audit, more mutations, or frame break.

Do not write any durable files. The goal here is situational awareness, not new state.

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. 3d ago First seen · 13 lines · 0 tokens per session scan A 6113018ac412

Subscribe to this mod's changes

why-stuck is a command published in the GitHub repository ProjectDXAI/labrat (238 stars, last pushed 26d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 164 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.

Related

Other commands, from other repositories