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/rshade/finfocus/code-reviewgit clone --depth 1 https://github.com/rshade/finfocusWhat 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 | $0.00010 | $0.01237 |
| Opus 5 | $0.00005 | $0.00619 |
| Sonnet 5 | $0.00002 | $0.00247 |
| Haiku 4.5 | $0.00001 | $0.00124 |
Grade A, and why
code-review 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review and Fix Protocol
Phase 1: Code Review
Use the golang-code-reviewer agent to perform a comprehensive review of recent changes focusing on:
Review Criteria
-
Code Quality and Best Practices
- Readability, maintainability, and adherence to Go best practices
- Proper error handling and return value checking
- Interface design and abstraction patterns
- Resource cleanup (defer statements, context handling)
-
Security Concerns
- Potential vulnerabilities or security issues
- Input validation and sanitization
- Secret handling and credential management
- File permissions and subprocess usage
-
Performance Considerations
- Potential performance bottlenecks
- Memory allocation patterns and efficiency
- Concurrent code safety and race conditions
- Algorithm complexity and optimization opportunities
-
Testing and Coverage
- Test coverage and quality assessment
- Edge case handling in tests
- Test organization and clarity
- Mock usage and test isolation
-
Documentation
- Package and exported type documentation
- Function comment completeness
- Code comment clarity and necessity
- README and architecture documentation
-
FinFocus-Specific Requirements
- Cross-repo consistency (spec, core, plugin alignment)
- Plugin protocol implementation correctness
- Cost calculation logic accuracy
- CLI UX and error messaging quality
-
Go Version Idioms (Go 1.25.6+)
- Use Go Go 1.25.6+ language features and standard library improvements
- Leverage modern Go patterns and best practices
- Ensure compatibility with Go Go 1.25.6+ runtime behavior
- Utilize updated standard library APIs and optimizations
Context for Review
- Current branch: !
git branch --show-current - Recent changes: !
git diff HEAD~1 - Recent commits: !
git log --oneline -5 - Current git status: !
git status - Current linting issues: !
make lint - Current test status: !
make test
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 · 158 lines · 10 tokens per session scan A aeb22e520502
code-review is a command published in the GitHub repository rshade/finfocus (5 stars, last pushed 16d ago), licensed Apache-2.0. It adds 10 tokens to every session and 1,237 once invoked, about $0.0001 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 commands, from other repositories
release-notes
Draft curated release notes for a milestone release.
create-issue
Create a GitHub issue from the repo's templates, with the right type and labels.
review-code
Review a GitHub pull request for the OpenOps codebase. Checks out the PR, analyzes changes through OpenOps-specific lenses, validates findings with confidence scoring, previews before posting, and supports inline comments.
soc2-review
Assess SOC 2 readiness against the Trust Services Criteria and produce a readiness dashboard.
scan
Scan AWS account for cost optimization.
costguard-audit
Audit registered workspaces for CI-minute and cron waste, plus read-only cloud provider billing checks. Quantifies estimated monthly waste and prints a Markdown (or JSON) report.