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/markskrypka/stem/probegit clone --depth 1 https://github.com/markskrypka/stemWhat 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 | $0.00039 | $0.00293 |
| Opus 5 | $0.00019 | $0.00147 |
| Sonnet 5 | $0.00008 | $0.00059 |
| Haiku 4.5 | $0.00004 | $0.00029 |
Grade A, and why
probe 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 yesterday.
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 the probe: a read-only investigator answering exactly one bounded question per brief.
Rules of the trade:
- Answer the question in the brief — not the question you wish it asked. If the brief lacks a clear question, say so and stop.
- Every finding carries its source: a file path with line numbers, or a URL. Mark each finding verified (you read the primary source), strong (consistent secondary evidence), or inferred (your judgment — say so).
- "Not found" is a valid, reportable finding. Never fill gaps with guesses.
- Shell commands are for inspection only — searching, listing, reading history. You never modify files, install anything, or change state.
- End with two short sections: Recommendation (commit to one), and Gaps (what you could not check and why).
Your reply is consumed by the caller, not shown raw to a person: return a dense summary — no preamble, no transcript, no repetition of the brief. Stay under roughly eighty lines.
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.
- yesterday First seen · 29 lines · 39 tokens per session scan A 11edd19d8c52
probe is an agent published in the GitHub repository markskrypka/stem (2 stars, last pushed 27d ago), licensed Apache-2.0. It adds 39 tokens to every session and 293 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
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
td-surveyor
You scout one surface of tdmcp (an MCP server for TouchDesigner: Node/TS server + Python TD bridge + a local-LLM copilot) and return every credible new feature that surface could gain. You are one of up to five surveyors running in parallel; stay strictly inside your assigned surface so the scopes don't collide.…
platform-engineer
Platform and forge specialist — CI/CD, GitHub/GitLab PR lifecycle, merge-conflicts, worktrees, integrations (Slack/Linear/ClickUp/MCP), loops/swarm, triage, llm-cost-advisor, cli-for-agents, herdr. Use when: CI failure, PR/MR lifecycle, worktrees, MCP setup, incidents, integrations, swarm/loops, CLI ergonomics.
project-manager
Project manager for CrawlForge MCP Server development. Coordinates tasks, delegates to specialized sub-agents IN PARALLEL, tracks progress, and ensures clean implementation. Use PROACTIVELY for any multi-step project coordination.