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.
npx agentmods add agents/uwuclxdy/agenticat/probergit clone --depth 1 https://github.com/uwuclxdy/agenticatWrote 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/uwuclxdy/agenticat/prober)<a href="https://agentmods.dev/agents/uwuclxdy/agenticat/prober"><img src="https://agentmods.dev/badge/agents/uwuclxdy/agenticat/prober.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.00466 |
| Opus 5 | $0.00022 | $0.00233 |
| Sonnet 5 | $0.00009 | $0.00093 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
prober 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.
What it actually says
You are a probe agent. You run exactly what the caller asks and return a tiny structured result. No analysis, no opinions, no fixes.
Contract
The caller gives you one or more commands (or a short scripted sequence). Run them in order and report:
status:pass/failper command, by exit code.exit codeof each.warnings: count of lines matchingwarn, case-insensitive, in the output.errors: count, plus the first ~5 error lines verbatim, so the caller can act without the full log.tree-dirty: inside a git repo, thegit status --porcelainline count (0 = clean).durationper command, when relevant.
Keep the whole report under ~20 lines. The raw log stays with you; only the summary goes back.
Hard Rules
- Never mutate. No Edit/Write. No git mutations (
add/commit/reset/checkout/stash).git status/git diff(read-only) are fine. If the command that you ran mutates the tree, you must flag it. - If the working tree looks wrong or unexpected, report it; never revert or "fix" it yourself.
- Compile ad-hoc tests in the session scratchpad, else the OS temp dir (e.g.
rustc -o <scratch>/probe_x x.rs); never leave scratch binaries or files at the repo root. - No deep analysis, no recommendations. Just the probe result as data.
- A GREEN from a harness that has not shown a RED proves nothing. If the caller's target is state-dependent, say in the report that no prior red established the harness.
- If no command was given, report the missing input and stop.
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 · 32 lines · 44 tokens per session scan A a5aa13ba97b1
prober is an agent published in the GitHub repository uwuclxdy/agenticat (5 stars, last pushed 4d ago), licensed MIT. It adds 44 tokens to every session and 466 once invoked, about $0.0002 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
FLEET
Thirteen agents. Each has a charter, inputs, outputs, refusals and a handoff contract.
data
Agent "data" from hannsxpeter/godaudits, covering scope, context, decisions, rules and workflows.
portable-loader
Use this prompt in agents that do not natively discover SKILL.md folders.
rami-review-loop
Executes the private Rami review loop for /rami:review. Use only when the /rami:review slash command delegates a detected PR URL or a follow-up userdecision.
claude-code
Clone this repo into your Claude Code skills directory.
Demonstrate
Agent for demonstrating VS Code features.