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/s3yed/appie-kit/codebase-audit-and-roadmapnpx skills add S3YED/appie-kit --skill codebase-audit-and-roadmapgit clone --depth 1 https://github.com/S3YED/appie-kitWrote 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/s3yed/appie-kit/codebase-audit-and-roadmap)<a href="https://agentmods.dev/skills/s3yed/appie-kit/codebase-audit-and-roadmap"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/codebase-audit-and-roadmap.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 | $0.00032 | $0.01559 |
| Opus 5 | $0.00016 | $0.00779 |
| Sonnet 5 | $0.00006 | $0.00312 |
| Haiku 4.5 | $0.00003 | $0.00156 |
Grade A, and why
codebase-audit-and-roadmap scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -H "Authorization: Bearer $VERCEL_TOKEN" \ How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Audit & Roadmap
When a user names a project and asks "what's in it" / "what's next" / "make a PRD" / "audit this" — this skill covers the full discovery-to-plan workflow.
When to Use
- User says "check this repo" or "audit this project"
- User names a project and asks for a feature summary or to "make a PRD"
- User asks for a gap analysis before a launch/rebuild
- User references a project you haven't encountered before and needs structured analysis
Workflow
Phase 1 — Locate the Project
- Ask / clarify what they mean — get a name, repo URL, or GitHub handle
- Search locally:
find ~ -maxdepth 4 -name ".git" -type d - Search GitHub: use web_search with
site:github.com <handle>patterns. Try known handles (S3YED, weblyfe, etc.) - Try multi-case variations — the exact case matters on GitHub. If user says "wai", search
S3YED/wai,s3yed/WAI, etc. - Clone private repos via SSH if SSH key is configured (
ssh -T [email protected]to verify) - Fallback: ask for the exact URL if web search fails
Phase 2 — Codebase Analysis (Systematic)
Read in this order, top to bottom:
- README.md — overall purpose, features, stack, setup
- AGENTS.md / CLAUDE.md / SKILL.md — project-specific instructions for agents
- package.json — dependencies, build scripts, test commands (run
npm ls 2>/dev/null | head) - Git log —
git log --oneline -10 --all— recent activity, branch structure - Project structure —
find src -maxdepth 2 -type d | sort, or list top-level files - Key feature files — read every component/API/hook file systematically:
api/*.ts— serverless endpoints (feature surface)components/*.tsx— UI screens (feature surface)utils/*.ts— shared logichooks/*.ts— custom hooksmigrations/*.sql— DB schema
- Types/interfaces — the data model tells you the domain
- Tests —
npm testorvitest run— test coverage is a health signal - Docs/ directory — PRDs, architecture docs, integration guides
- Existing PRDs (
docs/*PRD*.md,docs/*PLAN*.md) — read first to compare intent vs reality
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.
- yesterday First seen · 134 lines · 32 tokens per session scan A 0ea6610bad43
codebase-audit-and-roadmap is a skill published in the GitHub repository S3YED/appie-kit (7 stars, last pushed 9d ago), licensed MIT. It adds 32 tokens to every session and 1,559 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
internal-linking-optimizer
Use when improving internal link structure, anchor text, orphan pages, crawl depth, site architecture, or link equity flow. 内链优化/站内架构.
seo-geo-optimizer
Comprehensive SEO/GEO/AEO analysis toolkit for optimizing content visibility across traditional search engines (Google, Bing), AI platforms (ChatGPT, Perplexity, Claude, Gemini, Grokipedia), answer engines (Google AI Overviews, Bing Copilot, featured snippets), voice assistants (Google Assistant, Siri, Alexa), and…
geo-review-html
Render an interactive, self-contained HTML companion for a GEO content brief (04-content-brief) or a publish-ready draft (05-production), so a NON-technical client reviewer (founder, organizer staff, the domain expert filling slots) can fill REQUIRED-FILL slots, leave section-level comments, and approve/return work in…
geo-pipeline
Entry point + orchestrator for the recomby-geo GEO (Generative Engine Optimization) workflow on OpenAI Codex CLI. Use when the user wants to run any stage of the GEO pipeline on a client folder — intake, visibility audit, content-gap analysis, content brief, draft production, distribution, or monthly re-audit — or…
follow-up-writer
Use when drafting a post-event follow-up message to someone met at a conference.
schedule
Create, list, remove or inspect this bot's scheduled work — recurring jobs ("every morning at 7 tell me X", "every weekday at 9 post the standup") and one-shot follow-ups ("check back in 20 minutes", "watch that deploy until it lands", "remind me on Friday"). Use whenever something must happen on a schedule…