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-takeovergit 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-takeover)<a href="https://agentmods.dev/skills/iamsecure1920/cordon-ai/cordon-takeover"><img src="https://agentmods.dev/badge/skills/iamsecure1920/cordon-ai/cordon-takeover.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 | $0.00050 | $0.00804 |
| Opus 5 | $0.00025 | $0.00402 |
| Sonnet 5 | $0.00010 | $0.00161 |
| Haiku 4.5 | $0.00005 | $0.00080 |
Grade A, and why
cordon-takeover 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 6d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cordon subdomain takeover
Most takeover reports get closed as informative because the reporter skipped verification. A fingerprint on a page is not a takeover.
The three steps
1. Enumerate bbot_scan(preset="subdomain-enum") or subdomain_enum
2. Detect takeover_detect(hosts) → candidates (noisy, expect false positives)
dns_resolve(hosts) → CNAME with no A record, auto-queued
3. Verify takeover_verify(host) → all three checks must agree
takeover_verify requires:
- the CNAME chain resolves to a provider,
- the live page returns that provider's unclaimed-resource fingerprint,
- and the service is in the can-i-take-over-xyz data.
Anything short of that is not_a_candidate. Do not report it.
Severity
| Record | Severity | Why |
|---|---|---|
| NS with no address record | Critical | Whoever claims it controls the entire zone |
| MX matching a fingerprint | High | Mail interception |
| CNAME, provider claimable | High | Content control on a target hostname |
CNAME, provider edge-case |
Medium, often not a bug | Provider verifies ownership |
NS and MX coverage is conditional
The CNAME flow above runs on the tools that ship by default (subzy, dnsReaper). Lame NS delegation is not covered by any of them — HTTP-oriented scanners only see hosts that answer HTTP, and a broken delegation usually answers nothing at all.
subdomainsleuth is the tool for that, it needs authoritative zone files, and
it is not installed by default. Check before you claim coverage:
cordon doctor | grep subdomainsleuth
If it is absent, NS and MX delegation on this engagement is UNTESTED, not clean — say so in the report rather than letting a silent gap read as a negative result. That distinction is the same one the validators make when a binary is missing.
CloudFront, Netlify, Vercel, Shopify, and Fastly are marked edge-case: they
verify domain ownership, so the fingerprint appears but the takeover usually is
not possible. The verifier flags this and downgrades with a reason. Do not argue
past that flag — a wrong takeover report is expensive for the program's trust
in you.
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.
- 6d ago First seen · 89 lines · 50 tokens per session scan A 5b903eb7b5b3
cordon-takeover is a skill published in the GitHub repository iamsecure1920/Cordon-AI (0 stars, last pushed 3d ago), licensed MIT. It adds 50 tokens to every session and 804 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…