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 skills/abhinav503/flutter-agentic/review-codenpx skills add abhinav503/flutter-agentic --skill review-codegit clone --depth 1 https://github.com/abhinav503/flutter-agenticWhat 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 | $0.00084 |
| Opus 5 | $0.00000 | $0.00042 |
| Sonnet 5 | $0.00000 | $0.00017 |
| Haiku 4.5 | $0.00000 | $0.00008 |
Grade A, and why
review-code 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.
What it actually says
review-code
Run after any AI-generated code to catch rule violations before committing. Read the project rules, then audit the files the user just generated or modified.
If no files were specified, ask: "Which files or feature should I review?"
Then follow every check in the guide below and report a ✅/❌ checklist. Offer to fix each violation after reporting.
@docs/how-to/review-code.md
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 · 12 lines · 0 tokens per session scan A 9ac221068248
review-code is a skill published in the GitHub repository abhinav503/flutter-agentic (10 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 84 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 skills, from other repositories
language-typescript
TypeScript conventions with generic guidance plus a monorepo-specific addendum.
develop-opencode-plugins
OpenCode plugin development patterns, architecture, and conventions for implementing or extending plugins in this repo. Covers the native @opencode-ai/plugin surface (Plugin/PluginInput, tool(), hooks, auth, permissions) and this repo's house library layered on top.
workflow-git-cli
Practical Git CLI workflow conventions for branching, staging, diffing, committing, pushing, PR creation, and ignore hygiene.
write-skill
Conventions for authoring SKILL.md files. Load before creating or reviewing any skill.
workflow-agentic
Conventions for dispatching local opencode CLI runs as agentic workers - sync vs async, model selection, session continuity, thinking-partner pattern, and multi-model fanout.
write-command
Conventions for authoring OpenCode command files - frontmatter, structure, step design, tool routing, and constraint patterns.