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/iamcxa/kc-claude-plugins/doc-probegit clone --depth 1 https://github.com/iamcxa/kc-claude-pluginsWrote 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/iamcxa/kc-claude-plugins/doc-probe)<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>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 | $0.00033 | $0.00677 |
| Opus 5 | $0.00016 | $0.00338 |
| Sonnet 5 | $0.00007 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00068 |
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.
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 identifiersource_doc: which doc file makes this claimsection: which sectionclaim: human-readable description of the claimed behaviorprobe.method: "cli" or "skip"probe.command: the command to executeprobe.timeout: max seconds (default 30)expected: list of strings that should appear in output
Execution Protocol
For each claim where method = "cli":
-
Safety check: Reject if command contains destructive patterns (rm, delete, push, --force, reset, drop). Mark as
skipped: unsafe. -
Execute: Run via Bash with timeout.
- If command starts with
claude -p: add--no-inputflag 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
- If command starts with
-
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
-
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'" }
]
}
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.
- 3d ago First seen · 84 lines · 33 tokens per session scan A 3a52601f814c
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.
Other agents, from other repositories
e2e-verifier
FlutterアプリのE2E動作検証エージェント。MCP(dart-mcp + Marionette)を使い、シミュレーター上でUI操作・検証を行う。mobile-automationスキルから呼び出される。.
e2e-testing
pnpm expo run:ios pnpm expo run:android.
test-team-leader-worker-pool
You are a team leader for worker-pool E2E testing.
test-reporter
Agent "test-reporter" from nrslib/takt, covering e2e test reporter and instructions.
integration-testing-orchestrator
Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…
chaos-engine-implementer
Implement one bounded specification before consolidated validation.