Borrowing it
Nothing to install: this file belongs to ken-jo/agent-connector. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ken-jo/agent-connector/main/.claude/commands/discovery-check.mdgit clone --depth 1 https://github.com/ken-jo/agent-connectorWrote 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/ken-jo/agent-connector/discovery-check)<a href="https://agentmods.dev/commands/ken-jo/agent-connector/discovery-check"><img src="https://agentmods.dev/badge/commands/ken-jo/agent-connector/discovery-check/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/ken-jo/agent-connector/discovery-check"><img src="https://agentmods.dev/badge/commands/ken-jo/agent-connector/discovery-check.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 | $0.00041 | $0.01055 |
| Opus 5 | $0.00020 | $0.00528 |
| Sonnet 5 | $0.00008 | $0.00211 |
| Haiku 4.5 | $0.00004 | $0.00105 |
Grade A, and why
discovery-check 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 2d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run the agent-discovery check for agent-connector.ai and append ONE row to
docs/ops/discovery-log.md. Facts only — numbers you actually read from the tools,
"n/a" where a source is unavailable, no interpretation in the row itself. Put a
one-line factual note under the table only if something changed materially
(a query newly ranking, a bot newly fetching llms.txt, an index status flip).
Window: the last 7 full days ending yesterday (UTC). Site property:
sc-domain:agent-connector.ai (Search Console) / https://agent-connector.ai (Bing).
1. Google Search Console (gsc MCP — suganthan-gsc-mcp)
Site sc-domain:agent-connector.ai; use site_snapshot / advanced_search_analytics.
- Total impressions, clicks, average position for the window.
- Top 5 queries by impressions, and separately every query containing any of:
mcp,agent host,agent-connector,defineconnector,publish,deploy,install— with impressions, clicks, position. - Index status of
https://agent-connector.ai/andhttps://agent-connector.ai/llms.txt(URL inspection), (inspect_url).
2. Bing Webmaster Tools (bing-webmaster MCP)
get_query_statsreturns weekly buckets (theDatefield is an epoch-ms/Date(…)/string; the bucket dated at the window's end covers the window). Sum impressions and clicks over that bucket, and list queries from the keyword set.get_crawl_statsis daily: sumCrawledPagesandCrawlErrorsover the window, and report the latestInIndex.get_rank_and_traffic_statsandget_query_traffic_statsfail in server 1.0.2 with a pydanticdict_typeerror (the API returns a list); do not use them.
3. Cloudflare (cloudflare-graphql MCP)
Zone agent-connector.ai, same window, via the GraphQL Analytics API
(httpRequestsAdaptiveGroups): request counts for paths /llms.txt,
/llms-full.txt, /skills/agent-connector/SKILL.md, and / — grouped by
clientRequestHTTPHost/path and userAgent. Report the top user agents per
path, and single out these if present: ClaudeBot, Claude-User, anthropic-ai,
GPTBot, ChatGPT-User, OAI-SearchBot, PerplexityBot, Google-Extended, Googlebot,
bingbot, CCBot, Bytespider, Applebot-Extended.
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.
- 2d ago First seen · 70 lines · 41 tokens per session scan A 4ee834f9fdbd
discovery-check is a command published in the GitHub repository ken-jo/agent-connector (8 stars, last pushed 2d ago), licensed Apache-2.0. It adds 41 tokens to every session and 1,055 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 2026-09-06.
Other commands, from other repositories
harness-audit
Audit this repository's AI harness maturity with the deterministic harness-score scanner.
extract-profile
Extract a complete profile from an existing repo (runs the extract-profile skill).
rfc
Scaffold a new RFC in docs/rfc/proposed/.
review
Review the current changes with the code-reviewer subagent.
squadai-init
You are running the squadai squadai-init routine: read the current repository, understand what it actually contains, and refine each configured agent's role files (or solo instructions file) so they are tuned to this codebase — without losing any methodology semantics squadai installed.
memory-search
Search project memory for prior decisions, learnings, and incidents.