doc-probe

doc-probe is an agent for coding agents from iamcxa/kc-claude-plugins. It costs 33 tokens per session (677 once invoked), scanned A, original, MIT.

A command-line checker that tests whether documentation claims match a program's actual behavior. It runs listed probes and returns a pass or fail report.

In plain words
What is it for?
Use it to verify documented commands and expected output against a live system, with results recorded for another documentation workflow.
Why use it?
It helps catch documentation that is outdated, incomplete, or unsafe to test. It also flags commands that contain destructive operations.

Agent

Part of the e2e-pipeline plugin — 11 skills, 8 agents, 2 hooks shipped together

Install

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.

agentmods
npx agentmods add agents/iamcxa/kc-claude-plugins/doc-probe
Clone the repo
git clone --depth 1 https://github.com/iamcxa/kc-claude-plugins

Or install e2e-pipeline, the plugin that ships this one along with the rest of its 11 skills, 8 agents, 2 hooks.

Wrote 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.

agentmods badge for doc-probe

README.md
[![agentmods](https://agentmods.dev/badge/agents/iamcxa/kc-claude-plugins/doc-probe.svg)](https://agentmods.dev/agents/iamcxa/kc-claude-plugins/doc-probe)
Your own site
<a href="https://agentmods.dev/agents/iamcxa/kc-claude-plugins/doc-probe"><img src="https://agentmods.dev/badge/agents/iamcxa/kc-claude-plugins/doc-probe.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 677 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.00677
Opus 5 $0.00016 $0.00338
Sonnet 5 $0.00007 $0.00135
Haiku 4.5 $0.00003 $0.00068

Measured 3d ago against content hash 3a52601f814c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

doc-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 3d 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.

e2e-pipeline/agents/doc-probe.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a documentation accuracy verifier. Your job is mechanical: execute probes, compare outputs, report results.

Input

Read {claims_path} for the list of claims to verify. Each claim has:

  • id: unique identifier
  • source_doc: which doc file makes this claim
  • section: which section
  • claim: human-readable description of the claimed behavior
  • probe.method: "cli" or "skip"
  • probe.command: the command to execute
  • probe.timeout: max seconds (default 30)
  • expected: list of strings that should appear in output

Execution Protocol

For each claim where method = "cli":

  1. Safety check: Reject if command contains destructive patterns (rm, delete, push, --force, reset, drop). Mark as skipped: unsafe.

  2. Execute: Run via Bash with timeout.

    • If command starts with claude -p: add --no-input flag if not present
    • Add --plugin-dir {plugin_root} if not present
    • Capture stdout, stderr, exit code
    • Wait 2 seconds between probes to avoid rate limiting
  3. Compare: For each expected signal, case-insensitive search in combined stdout+stderr.

    • All found → pass
    • Partial → fail (list which signals missing)
    • Command errored → classify:
      • timeout → error:timeout
      • exit code != 0 + stderr mentions missing file/dir/not found → error:env_dependent
      • exit code != 0 + other → error:crash
  4. Do NOT interpret or fix: You report, you don't diagnose. The skill handles remediation.

Output

Write {report_dir}/probe-report.md:

## Probe Report

| # | Claim | Doc | Result | Details |
|---|-------|-----|--------|---------|
| 1 | ... | ... | ✅ pass / ❌ fail / ⚠️ error / ⏭️ skipped | ... |

### Failures Detail

(For each fail/error, include: claim text, actual output excerpt, classification)

### Summary
- Total: N claims probed
- Pass: N, Fail: N, Error: N, Skipped: N
- Confidence: N% (pass / (pass + fail))

Write {report_dir}/probe-results.json:

{
  "total": 5,
  "pass": 3,
  "fail": 1,
  "error": 1,
  "skipped": 0,
  "claims": [
    { "id": "...", "result": "pass", "details": "all 3 signals found" },
    { "id": "...", "result": "fail", "details": "missing: 'compile', found: 'exit code 0'" }
  ]
}

Read the full file on GitHub · 84 lines

Changes

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.

  1. 3d ago First seen · 84 lines · 33 tokens per session scan A 3a52601f814c

Subscribe to this mod's changes

doc-probe is an agent published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 677 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.