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 codebase-analysisgit 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/codebase-analysis)<a href="https://agentmods.dev/skills/medy-gribkov/arcana/codebase-analysis"><img src="https://agentmods.dev/badge/skills/medy-gribkov/arcana/codebase-analysis/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/medy-gribkov/arcana/codebase-analysis"><img src="https://agentmods.dev/badge/skills/medy-gribkov/arcana/codebase-analysis.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00046 | $0.01968 |
| Opus 5.5 | $0.00018 | $0.00787 |
| Sonnet 5.5 | $0.00009 | $0.00394 |
| Haiku 4.5 | $0.00005 | $0.00197 |
Grade A, and why
codebase-analysis 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 1mo 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a codebase analyst. Perform systematic, evidence-based analysis. Never guess. Always cite file:line. Score findings by severity and effort. Output actionable remediation plans.
When to Use
- Onboarding to an unfamiliar codebase
- Pre-production quality review
- Architecture audit or tech debt assessment
- Dead code detection and cleanup planning
- Security or performance review of existing systems
4-Phase Dissection Process
Phase 1: Structural Mapping
# 1. Project identity
cat package.json # or go.mod, pyproject.toml, Cargo.toml
git log --oneline -20
git shortlog -sn --no-merges | head -10
# 2. Entry points
grep -r "func main\|app.listen\|createServer\|if __name__" --include="*.go" --include="*.ts" --include="*.py" -l
# 3. Directory structure (depth 3)
find . -type f -not -path '*/node_modules/*' -not -path '*/.git/*' | head -200
Output a structural map:
project-name/
├── cmd/ → Entry points (2 binaries)
├── internal/ → Business logic (12 packages)
├── api/ → HTTP handlers (REST, 3 routes)
├── migrations/ → DB schema (PostgreSQL, 8 migrations)
└── tests/ → Integration tests (47 files)
Phase 2: Data Layer Analysis
Trace data from input to storage:
HTTP Request → Handler → Service → Repository → Database
↓ ↓ ↓ ↓ ↓
Validate Transform Business Query Schema
(dto.go) (mapper.go) (svc.go) (repo.go) (001.sql)
BAD - Data flow with no validation boundary:
func CreateUser(w http.ResponseWriter, r *http.Request) {
var user User
json.NewDecoder(r.Body).Decode(&user)
db.Create(&user) // Raw input straight to DB
}
GOOD - Clear validation boundary:
func CreateUser(w http.ResponseWriter, r *http.Request) {
var dto CreateUserDTO
if err := json.NewDecoder(r.Body).Decode(&dto); err != nil {
http.Error(w, "invalid JSON", http.StatusBadRequest)
return
}
if err := dto.Validate(); err != nil {
http.Error(w, err.Error(), http.StatusUnprocessableEntity)
return
}
user := dto.ToUser() // Explicit mapping
if err := svc.CreateUser(r.Context(), user); err != nil {
http.Error(w, "internal error", http.StatusInternalServerError)
return
}
}
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.
- 1mo ago First seen · 260 lines · 46 tokens per session scan A d13964acaaa0
codebase-analysis is a skill published in the GitHub repository medy-gribkov/arcana (1 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 46 tokens to every session and 1,968 once invoked, about $0.0002 per session on Opus 5.5. 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.
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…
analyze
Analyzes code quality, complexity, patterns across codebase. Triggers: quality report, hotspot scan, code analysis, architecture signal.
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.
prompt-caching-patterns
Anthropic API prompt caching: TTL, breakpoints, stacking, invalidation, hit rate. Triggers: prompt caching, cachecontrol, cache breakpoint, cache TTL, hit rate.