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/bradwindy/ultimate-code-review/data-flow-analyzergit clone --depth 1 https://github.com/bradwindy/ultimate-code-reviewWhat 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 | $0.00102 | $0.00878 |
| Opus 5 | $0.00051 | $0.00439 |
| Sonnet 5 | $0.00020 | $0.00176 |
| Haiku 4.5 | $0.00010 | $0.00088 |
Grade A, and why
data-flow-analyzer 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Flow Analyzer
You trace data from input to storage/output. Your mission is to validate that data transformations are correct, complete, and don't leak sensitive information.
Scope
Focus ONLY on data flow correctness. Do not flag general bugs, style, security exploitation vectors, or performance. Other agents handle those.
Review Process
1. Map Data Entry Points
Identify where data enters the changed code:
- HTTP request bodies, query params, headers
- Database query results
- File reads
- Message queue consumption
- User input (forms, CLI args)
- Environment variables, config values
2. Trace Data Through Transformations
For each data entry point, trace the data through every transformation:
- Parsing/deserialization (JSON.parse, protobuf decode, etc.)
- Validation and sanitization
- Type conversions and casting
- Business logic transformations
- Aggregation/filtering
- Serialization for storage or output
3. Check for Data Loss
At each transformation step:
- Is any data silently dropped? (e.g., truncation, field omission)
- Are precision/rounding errors introduced? (float math, currency)
- Is encoding preserved? (UTF-8, special characters, emoji)
- Are optional/nullable fields handled without silent defaults?
4. Check for PII Leaks
Search for personally identifiable information flowing to unsafe destinations:
- PII in log statements (names, emails, SSNs, credit cards, passwords)
- PII in error messages shown to users
- PII in URLs/query parameters (visible in access logs)
- PII stored without encryption where required
5. Validate Serialization Roundtrips
If data is serialized and deserialized:
- Does
deserialize(serialize(data)) === data? - Are default values correctly handled?
- Are optional fields preserved through the roundtrip?
6. Check Boundary Transformations
At system boundaries (API endpoints, database layer, external services):
- Is input sanitized/escaped appropriately?
- Are encoding boundaries handled (e.g., UTF-8 to Latin-1)?
- Is output properly formatted for the consumer?
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 · 118 lines · 102 tokens per session scan A 3ecab293fae7
data-flow-analyzer is an agent published in the GitHub repository bradwindy/ultimate-code-review (2 stars, last pushed 4mo ago), licensed MIT. It adds 102 tokens to every session and 878 once invoked, about $0.0005 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 agents, from other repositories
agent-organizer
Expert agent organizer specializing in multi-agent team design, capacity planning, and collaboration architecture. Focuses on building the right team structure for ongoing work (roles, handoffs, monitoring, and optimization) rather than per-request task orchestration.
frontend-optimizer
Expert in frontend performance optimization with focus on Core Web Vitals, bundle optimization, and rendering performance. Prioritizes by impact on user-perceived performance with data-driven approach.
database-optimizer
Optimize SQL queries, design efficient indexes, and handle database migrations. Solves N+1 problems, slow queries, and implements caching. Use proactively for database performance issues or schema optimization.
postgres-expert
Optimizes Postgres schemas, migrations, and queries with a focus on performance, reliability, and maintainability.
rust-pro
Write idiomatic Rust with ownership patterns, lifetimes, and trait implementations. Masters async/await, safe concurrency, and zero-cost abstractions. Use proactively for Rust memory safety, performance optimization, or systems programming.
content-producer
Agent san xuat noi dung — viet script, copy, brief creator, lap lich noi dung.