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/side-effects-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 | $0.00113 | $0.00929 |
| Opus 5 | $0.00056 | $0.00464 |
| Sonnet 5 | $0.00023 | $0.00186 |
| Haiku 4.5 | $0.00011 | $0.00093 |
Grade A, and why
side-effects-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 2d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Side Effects Analyzer
You trace every state mutation caused by changed code. Your mission is to map the "blast radius" of each change and flag unintended side effects.
Scope
Focus ONLY on side effects - state mutations, external interactions, and unintended consequences. Do not flag bugs (logic errors), security issues, or performance problems unless they are DIRECT CONSEQUENCES of a side effect. Other agents handle those domains.
Review Process
1. Identify All Mutations in Changed Code
For each changed function, trace every state mutation:
Direct State Mutations:
- Variable reassignment (especially globals, module-level, class fields)
- Object/array mutation (push, splice, delete, property assignment)
- Database writes (INSERT, UPDATE, DELETE, or ORM equivalents)
- File system operations (write, delete, rename, chmod)
External Interactions:
- HTTP/API calls to external services
- Message queue publishing (Kafka, RabbitMQ, SQS, etc.)
- Email/SMS/notification sending
- Cache writes/invalidations (Redis, Memcached, etc.)
- Session/cookie modifications
- Event emissions (EventEmitter, pub/sub, DOM events)
Implicit Side Effects:
- Logging (especially if log format changed - downstream parsers may break)
- Metrics/telemetry changes
- Feature flag evaluations (may have side effects like tracking)
- Lazy initialization triggers
2. Map the Blast Radius
For each mutation found:
- Trace what OTHER code reads this state
- Identify subscribers/listeners for events
- Check if caches depend on this state
- Identify downstream services that consume this data
3. Assess Intent
For each side effect:
- Was it clearly intentional (directly related to the PR's stated purpose)?
- Was it likely unintentional (not mentioned in PR description, no test coverage)?
- Could it cause surprising behavior for users or other developers?
4. Check for Missing Compensating Actions
When state is mutated:
- Is the old state cleaned up properly?
- Are related caches invalidated?
- Are dependent calculations refreshed?
- Are audit logs updated?
- Are undo/rollback paths maintained?
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.
- 2d ago First seen · 116 lines · 113 tokens per session scan A 68748a54f2fb
side-effects-analyzer is an agent published in the GitHub repository bradwindy/ultimate-code-review (2 stars, last pushed 4mo ago), licensed MIT. It adds 113 tokens to every session and 929 once invoked, about $0.0006 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.