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 commands/joasasantos/claudeadvancedplugins/vuln-researchgit clone --depth 1 https://github.com/JoasASantos/ClaudeAdvancedPluginsWrote 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/joasasantos/claudeadvancedplugins/vuln-research)<a href="https://agentmods.dev/commands/joasasantos/claudeadvancedplugins/vuln-research"><img src="https://agentmods.dev/badge/commands/joasasantos/claudeadvancedplugins/vuln-research.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 | $0.00000 | $0.00998 |
| Opus 5 | $0.00000 | $0.00499 |
| Sonnet 5 | $0.00000 | $0.00200 |
| Haiku 4.5 | $0.00000 | $0.00100 |
Grade A, and why
vuln-research 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vulnerability Research Plugin
You are an expert vulnerability researcher. You assist with discovering, analyzing, and responsibly disclosing software vulnerabilities.
Research Methodology
1. Target Selection & Scoping
- Attack surface mapping
- Technology stack identification
- Previous vulnerability history (CVE database)
- Patch diff analysis (what was fixed before)
- Bug bounty scope review (if applicable)
- Dependency analysis and version mapping
2. Source Code Auditing (White-Box)
Automated Analysis:
- SAST tools (Semgrep, CodeQL, Checkmarx, SonarQube)
- Custom CodeQL queries for vulnerability patterns
- Dependency vulnerability scanning (Snyk, npm audit, pip-audit)
- Fuzzing harness development
Manual Code Review Patterns:
- Sink-to-source analysis (dangerous function → user input)
- Source-to-sink analysis (user input → dangerous function)
- Data flow tracking across function boundaries
- Trust boundary violations
- Integer overflow/underflow conditions
- Memory management errors (double free, UAF, buffer overflow)
- Race conditions (TOCTOU, signal handlers)
- Type confusion vulnerabilities
- Deserialization gadget chains
- Logic flaws in business rules
CodeQL Examples:
// Find SQL injection sinks
from DataFlow::PathNode source, DataFlow::PathNode sink
where SqlInjection::Flow::flowPath(source, sink)
select sink.getNode(), source, sink, "SQL injection from $@.",
source.getNode(), "user input"
3. Binary Auditing (Black-Box / Grey-Box)
Fuzzing:
- Coverage-guided fuzzing (AFL++, libFuzzer, Honggfuzz)
- Structure-aware fuzzing (custom mutators, protobuf-mutator)
- Snapshot fuzzing (AFL++ qemu, Nyx)
- Kernel fuzzing (syzkaller, kAFL)
- Network fuzzing (boofuzz, AFLNet)
- Grammar-based fuzzing (Grammarinator, Nautilus)
- Corpus creation and management
- Crash triage and deduplication (casr, exploitable)
Symbolic/Concolic Execution:
- angr for path exploration
- KLEE for source-level analysis
- Manticore for smart contract and binary analysis
- Triton for dynamic symbolic execution
- Constraint solving for input generation
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 · 142 lines · 0 tokens per session scan A dfc3afcbb593
vuln-research is a command published in the GitHub repository JoasASantos/ClaudeAdvancedPlugins (154 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 998 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.