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 agents/morodomi/dev-crew/false-positive-filter-referencegit clone --depth 1 https://github.com/morodomi/dev-crewWhat 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 | $0.00000 | $0.01302 |
| Opus 5 | $0.00000 | $0.00651 |
| Sonnet 5 | $0.00000 | $0.00260 |
| Haiku 4.5 | $0.00000 | $0.00130 |
Grade A, and why
false-positive-filter-reference 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 yesterday.
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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
False Positive Filter - Reference
false-positive-filter.md の Filter Rules 詳細定義・Output Format・統合ガイド。必要時のみ参照。
Input Format
security-scan出力（vulnerabilities配列）を入力として受け取る:
{
"vulnerabilities": [
{
"id": "XSS-001",
"type": "reflected",
"vulnerability_class": "xss",
"severity": "high",
"file": "app/views/user.blade.php",
"line": 23,
"code": "{{ $input }}"
}
]
}
@security-ignore Format
// @security-ignore reason="false positive - input from trusted source" reviewer="john"
| Attribute | Required | Description |
|---|---|---|
| reason | Yes | 除外理由（必須） |
| reviewer | Yes | レビュー承認者（必須） |
属性なしの@security-ignoreはconfidence 0.50（手動レビュー必須）
Sanitization Patterns by Language
sanitization_patterns:
php:
xss:
- 'htmlspecialchars\s*\('
- 'htmlentities\s*\('
- 'strip_tags\s*\('
- '\{\{\s*\$' # Blade auto-escape
- 'e\s*\(' # Laravel helper
sql-injection:
- '->where\s*\([^,]+,\s*\?'
- '->whereRaw\s*\([^,]+,\s*\['
- 'DB::select\s*\([^,]+,\s*\['
python:
xss:
- 'escape\s*\('
- '\{\{[^|]*\}\}' # Jinja2 auto-escape
# Note: mark_safe は除外対象外（エスケープ無効化のため脆弱）
sql-injection:
- 'execute\s*\([^,]+,\s*\['
- 'execute\s*\([^,]+,\s*\('
- '\.filter\s*\(' # Django ORM
javascript:
xss:
- 'textContent\s*='
- 'encodeURIComponent\s*\('
- 'DOMPurify\.sanitize\s*\('
sql-injection:
- '\?\s*,' # Parameterized query
- '\$\d+' # Positional parameter
Output Format
{
"metadata": {
"scan_id": "<uuid>",
"filtered_at": "<timestamp>",
"agent": "false-positive-filter"
},
"filtered_vulnerabilities": [
{
"id": "SQLI-001",
"severity": "high",
"file": "app/Controllers/UserController.php",
"line": 45
}
],
"false_positives": [
{
"id": "XSS-001",
"original_severity": "high",
"reason": "Sanitized by Blade auto-escape ({{ }})",
"filter_type": "pattern",
"pattern_matched": "\\{\\{\\s*\\$",
"confidence": 0.95
},
{
"id": "SQLI-002",
"original_severity": "medium",
"reason": "Test code (/tests/)",
"filter_type": "path",
"pattern_matched": "/tests/",
"confidence": 1.00
}
],
"summary": {
"original_count": 15,
"filtered_count": 12,
"false_positive_count": 3,
"filter_rate": "20%"
}
}
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.
- yesterday First seen · 188 lines · 0 tokens per session scan A 6083f53f00be
false-positive-filter-reference is an agent published in the GitHub repository morodomi/dev-crew (1 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,302 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 2026-08-31.
Other agents, from other repositories
gem-orchestrator
The team lead: Orchestrates planning, implementation, and verification.
nw-acceptance-designer
Use for DISTILL wave — designs E2E acceptance tests from user stories and architecture using Given-When-Then format. EXPANDED scope (plan v3 §3.A, 2026-05-19) — exclusive test-expertise owner; authors ATs with maximum PBT + parametrize density, runs self-completeness audit (7-category taxonomy + 15-item checklist)…
gem-browser-tester
E2E browser testing, UI/UX validation, visual regression.
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
nw-data-engineer
Use for database technology selection, data architecture design, query optimization, schema design, security implementation, and governance guidance. Provides evidence-based recommendations across RDBMS and NoSQL systems.
nw-ddd-architect
Use for DESIGN wave domain modeling. Discovers bounded contexts, designs aggregates, facilitates Event Modeling sessions, and recommends ES/CQRS when warranted. Writes to architecture SSOT.