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 skills add medy-gribkov/arcana --skill code-reviewergit clone --depth 1 https://github.com/medy-gribkov/arcanaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/medy-gribkov/arcana/code-reviewer)<a href="https://agentmods.dev/skills/medy-gribkov/arcana/code-reviewer"><img src="https://agentmods.dev/badge/skills/medy-gribkov/arcana/code-reviewer.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00035 | $0.02034 |
| Opus 5 | $0.00017 | $0.01017 |
| Sonnet 5 | $0.00007 | $0.00407 |
| Haiku 4.5 | $0.00003 | $0.00203 |
Grade A, and why
code-reviewer 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 8d 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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Determine Review Target
Remote PR: User provides a PR number or URL (e.g., "Review PR #123").
Local changes: User asks to "review my changes" or no PR is specified.
Review Workflow
For Remote PRs
- Checkout the PR branch.
gh pr checkout 123
- Run preflight checks to catch automated failures early.
npm run preflight
- Read PR description and existing comments to understand context.
gh pr view 123
For Local Changes
- Check git status and read diffs.
git status
git diff # Working tree changes
git diff --staged # Staged changes
- Optionally run preflight if changes are substantial.
npm run preflight
Review Pillars
Correctness
What to flag: Logic errors, incorrect assumptions, missing edge case handling.
Example review comment:
// File: src/orders/calculateTotal.ts:15
function calculateTotal(items: Item[]): number {
return items.reduce((sum, item) => sum + item.price, 0);
}
Flag: This does not account for quantity. If an item has quantity: 3, it should multiply price * quantity.
Suggested fix:
function calculateTotal(items: Item[]): number {
return items.reduce((sum, item) => sum + item.price * item.quantity, 0);
}
Maintainability
What to flag: Complex functions, unclear naming, duplicate logic, missing abstractions.
BAD:
// File: src/users/api.ts:42
async function handle(req: Request, res: Response) {
const u = await db.query('SELECT * FROM users WHERE id = ?', [req.params.id]);
if (!u) return res.status(404).send('Not found');
if (req.user.id !== u.id && req.user.role !== 'admin') {
return res.status(403).send('Forbidden');
}
res.json(u);
}
Flag: Function name handle is vague. Variable u is unclear. Authorization logic is inline and will be duplicated across routes.
GOOD:
async function getUserById(req: Request, res: Response) {
const user = await findUserById(req.params.id);
if (!user) return res.status(404).send('User not found');
if (!canAccessUser(req.user, user)) {
return res.status(403).send('Access denied');
}
res.json(user);
}
function canAccessUser(requester: User, target: User): boolean {
return requester.id === target.id || requester.role === 'admin';
}
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 316 lines · 35 tokens per session scan A 186aa016ab4b
code-reviewer is a skill published in the GitHub repository medy-gribkov/arcana (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 2,034 once invoked, about $0.0002 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 skills, from other repositories
code-reviewer
Perform thorough code reviews — bugs, security issues, performance bottlenecks, style violations, and architectural concerns.
security-auditor
Audit code for security vulnerabilities — OWASP Top 10, injection flaws, auth issues, secrets exposure, and dependency risks.
clean-code
Code quality: meaningful names, SRP, DRY, small functions, guard clauses, refactoring. Triggers: clean code, naming, code smell, SRP, DRY, long function, god class, dead code.
analyze
Analyzes code quality, complexity, patterns across codebase. Triggers: quality report, hotspot scan, code analysis, architecture signal.
prompt-caching-patterns
Anthropic API prompt caching: TTL, breakpoints, stacking, invalidation, hit rate. Triggers: prompt caching, cachecontrol, cache breakpoint, cache TTL, hit rate.
pr-review
AUTHOR SKILL (internal to microsoft/aspire-skills). Reviews pull requests into this repo for problems only — bugs, regressions, missing eval coverage, frontmatter or routing damage, plugin-manifest drift, hook safety, and other concrete issues. Drives a six-step workflow: identify the PR, ensure the branch is…