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 skills add iamsecure1920/Cordon-AI --skill cordon-recongit clone --depth 1 https://github.com/iamsecure1920/Cordon-AIWrote 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/skills/iamsecure1920/cordon-ai/cordon-recon)<a href="https://agentmods.dev/skills/iamsecure1920/cordon-ai/cordon-recon"><img src="https://agentmods.dev/badge/skills/iamsecure1920/cordon-ai/cordon-recon.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 5.1 | $0.00052 | $0.00757 |
| Opus 5 | $0.00026 | $0.00378 |
| Sonnet 5 | $0.00010 | $0.00151 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
cordon-recon 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 7d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cordon recon
Goal: turn a scope entry into a ranked list of things worth attacking, spending as few of the program's requests as possible.
Order
bbot_scan(seed, preset="subdomain-enum") # passive, broadest coverage
→ dns_resolve(hosts) # which names actually exist
→ cdn_check(hosts) # which are origin vs edge
→ http_probe(hosts) # which serve something
→ endpoint_discovery(domain) # archives: free URLs and params
→ js_analyze(js_urls) # bundles: hidden endpoints, keys
Then taskgraph_next() — discoveries have queued follow-up work with reasons
attached.
Choosing a BBOT preset
subdomain-enum— always start here.cloud-enum— add when the target clearly runs on AWS/Azure/GCP.code-enum— add when the org publishes code; feedssource_fetch.baddns— add when you want takeover candidates early.
Active presets need bbot_scan_active and human approval. Justify them: on an
unmapped surface they spend the rate limit on hosts you cannot yet rank.
Gap-filling
BBOT covers most of this. Reach for the atomic tools when it is absent or you want one specific source:
| Need | Tool |
|---|---|
| Subdomains without BBOT | subdomain_enum |
| Netblocks and ASN | asn_lookup (ownership ≠ authorization) |
| Certificate SANs | tls_info |
| Registrant / confirm ownership | whois_lookup |
| Names no source knows | dns_permute (aggressive — brute force over DNS) |
What to look for
Rank the surface, do not just list it:
- Non-standard hosts —
admin.,staging.,internal.,legacy.,old.,test.,vpn.,jira.. These are where policy is weakest. - Technology outliers — one host on a different stack from the other fifty usually means a different team, a different review process, or an acquisition.
- Parameters from archives —
endpoint_discovery'sunique_parametersis the cheapest lead in the run.url=,redirect=,next=,file=,id=,template=each point at a specific bug class. - Endpoints only present in JS — an API path a crawler never sees is a path nobody tested.
- CNAMEs with no address record — takeover candidates; they auto-spawn a verification task.
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.
- 7d ago First seen · 76 lines · 52 tokens per session scan A 9251e2797ac9
cordon-recon is a skill published in the GitHub repository iamsecure1920/Cordon-AI (0 stars, last pushed 4d ago), licensed MIT. It adds 52 tokens to every session and 757 once invoked, about $0.0003 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…