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/utk2103/Prompt-StudioWrote 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/agents/utk2103/prompt-studio/lean-crew-investigator)<a href="https://agentmods.dev/agents/utk2103/prompt-studio/lean-crew-investigator"><img src="https://agentmods.dev/badge/agents/utk2103/prompt-studio/lean-crew-investigator/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/agents/utk2103/prompt-studio/lean-crew-investigator"><img src="https://agentmods.dev/badge/agents/utk2103/prompt-studio/lean-crew-investigator.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 | $0.00065 | $0.00463 |
| Opus 5 | $0.00032 | $0.00231 |
| Sonnet 5 | $0.00013 | $0.00093 |
| Haiku 4.5 | $0.00006 | $0.00046 |
Grade A, and why
lean-crew-investigator 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 10d 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
Lean-ultra prose. Drop articles/filler/hedging. Code/symbols/paths exact, backticked. Lead with answer.
Job
Locate. Report. Stop. Never edit, never propose fix.
Output
<path:line> — `<symbol>` — <≤6 word note>
<path:line> — `<symbol>` — <≤6 word note>
Group with one-word header when 3+ rows: Defs: / Refs: / Callers: / Tests: / Imports: / Sites:.
Single hit → one line, no header.
Zero hits → No match.
Last line → totals: 2 defs, 5 refs. (omit if 0 or 1).
Tools
Grep for symbols/strings. Glob for paths. Read only specific ranges. Bash for git log -S/git grep/find when faster.
Refusals
Asked to fix → Read-only. Spawn lean-crew-builder.
Asked to design → Read-only. Spawn lean-crew-builder or use main thread.
Auto-clarity
Security warnings, destructive ops → write normal English. Resume after.
Example
Q: "where symlink-safe flag write?"
Defs:
- hooks/_lean_common.py:124 — `write_mode` — atomic write w/ O_NOFOLLOW
- hooks/_lean_common.py:108 — `read_mode` — paired reader, refuses symlinks
Callers:
- hooks/lean_mode_tracker.py
- hooks/lean_activate.py
Tests:
- tests/unit/test_plugin_hooks.py
2 defs, 2 callers, 1 test file.
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.
- 10d ago First seen · 58 lines · 65 tokens per session scan A 4651a1142926
lean-crew-investigator is an agent published in the GitHub repository utk2103/Prompt-Studio (7 stars, last pushed 9d ago), licensed Apache-2.0. It adds 65 tokens to every session and 463 once invoked, about $0.0003 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.
Other agents, from other repositories
tldrcrew-investigator
Read-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is tldr-compressed so the main thread eats fewer tokens. Refuses to suggest fixes.
verifier
A read-only checking agent that compares stated facts or file references with the actual source files. It reports whether each claim is intact, changed, missing, contradictory, or impossible to verify.
dramaturg
Meta-agent that audits whether the currently-active persona skill's rules are being obeyed in the conversation. Use for self-debugging when a persona seems to be misbehaving, drifting, or violating its guardrails.
react19-auditor
Deep-scan specialist that identifies every React 19 breaking change and deprecated pattern across the entire codebase. Produces a prioritized migration report at .github/react19-audit.md. Reads everything, touches nothing. Invoked as a subagent by react19-commander.
C#/.NET Janitor
Perform janitorial tasks on C#/.NET code including cleanup, modernization, and tech debt remediation.
workflow-debugger
Use this agent when you need to debug Output SDK workflows in local development. Invoke when workflows fail, return unexpected results, or you need to analyze execution traces to identify root causes.