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 MingyiSecLab/Mingyi-Atlas --skill pattern-exhaustiongit clone --depth 1 https://github.com/MingyiSecLab/Mingyi-AtlasWrote 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/mingyiseclab/mingyi-atlas/pattern-exhaustion)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/pattern-exhaustion"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/pattern-exhaustion/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/skills/mingyiseclab/mingyi-atlas/pattern-exhaustion"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/pattern-exhaustion.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 | $0.00033 | $0.01311 |
| Opus 5 | $0.00016 | $0.00656 |
| Sonnet 5 | $0.00007 | $0.00262 |
| Haiku 4.5 | $0.00003 | $0.00131 |
Grade A, and why
pattern-exhaustion 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 12d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pattern Exhaustion
When you find a vulnerability, you have found a PATTERN. The same developer who wrote one broken auth check likely wrote twenty. The same framework that misses one guard has a systemic design gap. One root cause → multiple CVEs.
Real-world examples:
- Parse Server: 4 advisories from guard bypass patterns (prototype chain, falsy-value guard, protected-field bypass, complexity validator)
- zrok: 3 advisories from access control (symlink traversal, broken ownership, reflected XSS in callback)
- AVideo: 3 advisories from deployment config (SSRF, exposed installer, memcached session leak)
The Exhaustion Loop
1. Classify the root cause
After confirming a vulnerability, classify its root cause pattern:
| Root Cause | Search Pattern |
|---|---|
| Missing auth/authz check | grep -rn 'def handle_|router\.\(get|post|put|delete\)' | grep -v 'auth|permission|require|middleware' |
| Unvalidated path parameter | grep -rn 'req\.params|request\.args|ctx\.params' | grep -v 'sanitize|validate|path\.resolve|path\.normalize' |
| SQL string interpolation | grep -rn 'f"SELECT|f"INSERT|f"UPDATE|query(.*\+.*|query(.*\$\{' --include='*.py' --include='*.ts' --include='*.js' |
| shell: true with user input | grep -rn 'shell:\s*true|shell=True|os\.system|subprocess\.call.*shell' --include='*.py' --include='*.ts' --include='*.js' |
| Missing ownership validation | grep -rn 'delete|update|modify' --include='*.py' --include='*.ts' | grep -v 'owner|author|created_by|user_id.*==' |
| Default-open feature flag | grep -rn 'enabled.*=.*false|feature.*disabled|trust.*=.*true' --include='*.ts' --include='*.py' |
| Unsafe deserialization | grep -rn 'pickle\.loads|yaml\.load|yaml\.unsafe|unserialize|JSON\.parse.*reviver|eval(' --include='*.py' --include='*.js' --include='*.php' |
| Type confusion in guard | grep -rn 'typeof.*==|instanceof|is_array|Array\.isArray' --include='*.ts' --include='*.js' --include='*.php' |
| Missing CSRF/state check | grep -rn 'state=|csrf|nonce' --include='*.py' --include='*.ts' | grep -v 'verify|validate|check' |
| Prototype pollution | grep -rn 'Object\.assign|merge(|extend(|deepMerge|_.merge|lodash' --include='*.js' --include='*.ts' |
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.
- 12d ago First seen · 107 lines · 33 tokens per session scan A 5d7e78bc753e
pattern-exhaustion is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,311 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 2026-08-30.
Other skills, from other repositories
cis-aws-foundations-6.5
Ensure the default security group of every VPC restricts all traffic.
cis-aws-foundations-4.3
Ensure AWS Config is enabled in all regions.
cis-aws-foundations-2.1.3
Ensure Organizations management account is not used for workloads.
cis-aws-foundations-2.5
Ensure MFA is enabled for the 'root' user account.
cis-aws-foundations-2.7
Eliminate use of the 'root' user for administrative and daily tasks.
cis-aws-foundations-4.4
Ensure that server access logging is enabled on the CloudTrail S3 bucket.