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/audit-candidate)<a href="https://agentmods.dev/commands/projectdxai/labrat/audit-candidate"><img src="https://agentmods.dev/badge/commands/projectdxai/labrat/audit-candidate/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/audit-candidate"><img src="https://agentmods.dev/badge/commands/projectdxai/labrat/audit-candidate.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 | $0.00167 |
| Opus 5.5 | $0.00000 | $0.00067 |
| Sonnet 5.5 | $0.00000 | $0.00033 |
| Haiku 4.5 | $0.00000 | $0.00017 |
Grade A, and why
audit-candidate 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 2mo 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
Walk the highest-signal suspicious candidate through an implementation audit.
- Read
state/frontier.json.audit_queueandstate/frontier.json.invalid_fast_candidates. - Pick the candidate with the highest
search_evalamong the suspicious set. Read its record fromstate/candidates.jsonland its evaluation fromstate/evaluations.jsonl, plus anycheckpoints.jsonlunder itsartifact_dir. - Read
implementation_audit.md. - Decide: is this a real bug, a real regression, or a misclassification?
- Leave an audit note under
logs/audits/<candidate_id>.mdand, if the candidate should re-enter the frontier, clear it fromaudit_queuewith the appropriate runtime command.
Do not change scores. The runtime is authoritative.
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.
- 2mo ago First seen · 10 lines · 0 tokens per session scan A 86bb67ed7103
audit-candidate is a command published in the GitHub repository ProjectDXAI/labrat (236 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 167 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
report-bug
Report a bug in the Lavra plugin.
yolo-abort
Immediate halt of /yolo Hive session mid-action — partial state saved, in-flight git operations rolled back where possible, audit log finalized with abort flag.
bugfix
TDD-driven bugfix workflow: tester writes failing test (RED) → developer fixes (GREEN) → developer refactors (REFACTOR) → reviewer validates. Accepts issue number, description, or both. Asks before pushing and creating a PR; --no-pr commits locally without asking.
fix-test
Auto-diagnose and fix failing tests — identifies root causes and applies fixes.
code-quality
Code review and bug prediction — find quality issues, style violations, and likely bugs.
refactor
Code-level refactoring analysis and roadmap generation.