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/ds1/probeWrote 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/ds1/probe/go)<a href="https://agentmods.dev/commands/ds1/probe/go"><img src="https://agentmods.dev/badge/commands/ds1/probe/go/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/ds1/probe/go"><img src="https://agentmods.dev/badge/commands/ds1/probe/go.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 | $0.00011 | $0.00637 |
| Opus 5.5 | $0.00004 | $0.00255 |
| Sonnet 5.5 | $0.00002 | $0.00127 |
| Haiku 4.5 | $0.00001 | $0.00064 |
Grade A, and why
go 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Probe: Full Analysis
Run six independent lens agents against one input, then synthesize their findings. Each lens prompt lives in its own agent under agents/; this command only parses arguments, launches, and reports.
Arguments
$ARGUMENTS holds the input and, optionally, an output directory. Parse it in this order:
- If
--out <dir>appears anywhere, that is the output directory. Remove it before the next step. - If what remains starts with a quoted string, the quoted string is the input path. Otherwise, if the first whitespace-delimited token is an existing file, that token is the input path, and a second token (when present and no
--outwas given) is the output directory. - If neither matched, the entire remaining text is the input, to be analyzed directly as pasted text.
- If no output directory was given, use
./probe-output/. Create it if it does not exist.
Paths that contain spaces must be quoted.
Step 1: launch the six lenses in parallel
Use the Agent tool to launch all six subagents in a single message so they run concurrently. They share no context with each other or with you.
subagent_type |
writes |
|---|---|
probe:clarify-thinking |
probe-clarify-thinking.md |
probe:challenge-assumptions |
probe-challenge-assumptions.md |
probe:evidence-basis |
probe-evidence-basis.md |
probe:alternative-viewpoints |
probe-alternative-viewpoints.md |
probe:implications-consequences |
probe-implications-consequences.md |
probe:question-the-question |
probe-question-the-question.md |
If the probe:-prefixed agent types are not available (the files were installed by script rather than as a plugin), use the same name without the prefix.
Give every agent the same launch prompt, varying only the output file name:
- Source: the input path to read, or the full pasted text.
- Output:
<output-dir>/<file from the table>. - Grounding: if the source cites function names, constants, file paths, or schema columns, add: "Verify any specific code claims against the actual code at the cited paths; do not take the source's claims about its own codebase at face value."
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.
- 1mo ago First seen · 49 lines · 11 tokens per session scan A df17e82f704d
go is a command published in the GitHub repository ds1/probe (3 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 637 once invoked, about $0.0000 per session on Opus 5.5. 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 commands, from other repositories
review
Run the full review gate locally and trigger CI visibility.
skill-eval
Validate and audit quality of AI agent slash commands and skills — checks YAML frontmatter, description length, jargon, directive verbs, and duplicates. Run after adding or editing commands.
adclaw-host-ai-accounting
Review AdClaw Host AI quota accounting, hosted keys, limit UX, and redaction boundaries.
code-review-team
Parallel multi-agent code review with 4 specialized reviewers (requires Claude Code Agent Teams).
rv
Run the local review gate before pushing.
review
Recent git commits: !git log --oneline -10.