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 skills/iamsecure1920/cordon-ai/cordon-validatenpx skills add iamsecure1920/Cordon-AI --skill cordon-validategit 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-validate)<a href="https://agentmods.dev/skills/iamsecure1920/cordon-ai/cordon-validate"><img src="https://agentmods.dev/badge/skills/iamsecure1920/cordon-ai/cordon-validate.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 | $0.00054 | $0.00827 |
| Opus 5 | $0.00027 | $0.00413 |
| Sonnet 5 | $0.00011 | $0.00165 |
| Haiku 4.5 | $0.00005 | $0.00083 |
Grade A, and why
cordon-validate 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cordon validation
No PoC, no finding. A candidate becomes confirmed only through
validate_findings, poc_record, or takeover_confirm. Nothing else can set
that status.
The rule that governs every PoC
The smallest proof that settles the question.
Proving SQL injection means showing 1 AND 1=1 and 1 AND 1=2 differ, or that a
SLEEP(5) delays the response. It does not mean dumping the users table. The
extra step adds no evidence, converts a clean report into a data-handling
incident, and is exactly what programs mean by "do not exfiltrate".
This is enforced, not advised: sqlmap's data-extraction flags (--dump, --dbs,
--tables, --file-read) are absent from its argument allowlist. No approval
can produce an extraction run.
Automatic validation
validate_findings(min_severity="medium") # exploit mode, needs approval
xss_validate(url) # dalfox, verifies execution
sqli_validate(url) # detection only
oob_listener() # callback domain for blind classes
Validators run in parallel, one per vulnerability class. Each returns proven or
not-proven with a reason. Not-proven downgrades the finding to
needs_manual_review with that reason attached — which is a useful result, not a
failure.
Classes that need a human, by design
| Class | Why automation stops |
|---|---|
| IDOR / authz | Proving it means reading another user's data |
| Auth bypass | Proving it means being someone else |
| RCE | Proving it means executing code on their host |
| Blind SSRF | Needs an out-of-band listener and injection context |
For these, reproduce by hand with the least impact that demonstrates the issue, then:
poc_record(
finding_id=...,
reproduction="GET /api/users/2 with user A's session cookie",
expected_result="403 Forbidden",
observed_result="200 OK returning user B's email address",
impact_limit_note="Read one adjacent record to prove the flaw; nothing retained.",
)
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 · 91 lines · 54 tokens per session scan A d0cdedde7025
cordon-validate is a skill published in the GitHub repository iamsecure1920/Cordon-AI (0 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 827 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…