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/dynamic-verifiergit 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 | $0.00036 | $0.02400 |
| Opus 5 | $0.00018 | $0.01200 |
| Sonnet 5 | $0.00007 | $0.00480 |
| Haiku 4.5 | $0.00004 | $0.00240 |
Grade C, and why
dynamic-verifier scanned grade C with 2 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.
Cloud metadata endpointhighServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
- "Cloud metadata (169.254.169.254)" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -i` | Content-Type: allow `text/html*`, skip `application/json|text/xml|application/xml` | redirect: `-L`, max 5 How it starts
The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Common Settings
rate_limiting: 2s, max_requests: 50, timeout: 10s, connect_timeout: 5s
Common Pre-processing
curl -i | Content-Type: allow text/html*, skip application/json|text/xml|application/xml | redirect: -L, max 5
Detection Target
| Type | Verification Method | Flag |
|---|---|---|
| SQLi | エラーベース検出（' 挿入→SQLエラーメッセージ確認） |
--dynamic |
| XSS | 反射検出（ペイロード挿入→レスポンスで反射確認） | --enable-dynamic-xss |
| Auth | 認証バイパス検出（認証なしで保護リソースアクセス確認） | --enable-dynamic-auth |
| CSRF | CSRFトークン検証（トークンなしリクエスト受理確認） | --enable-dynamic-csrf |
| SSRF | コールバック検出（外部URL指定→コールバック受信確認） | --enable-dynamic-ssrf |
| File | ファイル読取検出（パストラバーサル→既知ファイル内容確認） | --enable-dynamic-file |
SQLi Detection Patterns
sqli_error_patterns:
- "SQL syntax" # MySQL
- "mysql_fetch" # MySQL
- "ORA-" # Oracle
- "pg_query" # PostgreSQL
- "sqlite3" # SQLite
- "SQLSTATE" # PDO
Non-Destructive Payloads
sqli_payloads:
error_based:
- "'" # Single quote - syntax error trigger
- "1' OR '1'='1" # Boolean-based (read-only)
- "1 AND 1=1" # Numeric injection test
# Forbidden payloads (never use)
forbidden:
# Data destruction
- "DROP"
- "DELETE"
- "TRUNCATE"
- "UPDATE"
- "INSERT"
# Schema modification
- "ALTER"
- "CREATE"
# System operations
- "EXEC"
- "EXECUTE"
- "LOAD_FILE"
- "INTO OUTFILE"
# Comments / multi-statement
- "; --"
- "/*"
- "--"
- "#" # MySQL comment
Safety Measures
| Risk | Mitigation | Implementation |
|---|---|---|
| Production attack | --target required | Exit if URL not specified |
| Destructive payload | Non-destructive only | Check against forbidden list |
| Overload | Rate limiting | sleep 1 between requests |
| Unintended attack | URL validation | Confirm if not localhost |
URL Validation Logic
url_validation:
allowed_schemes: [http, https]
safe_hosts: [localhost, 127.0.0.1, "::1", "[::1]"] # 0.0.0.0 excluded (production risk)
confirmation_required: "All other hosts → WARNING: Target is not localhost. Continue? (y/N)"
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 · 292 lines · 36 tokens per session scan C ab9e7197847f
dynamic-verifier is an agent published in the GitHub repository morodomi/dev-crew (1 stars, last pushed 3d ago), licensed MIT. It adds 36 tokens to every session and 2,400 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (cloud metadata endpoint, makes network calls). 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.