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/quangphu1912/codebase-analyzer/classify-analysis-targetnpx skills add quangphu1912/codebase-analyzer --skill classify-analysis-targetgit clone --depth 1 https://github.com/quangphu1912/codebase-analyzerWhat 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 | $0.00026 | $0.00698 |
| Opus 5 | $0.00013 | $0.00349 |
| Sonnet 5 | $0.00005 | $0.00140 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
classify-analysis-target 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 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.
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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Announce at start: "Using codebase-analyzer to classify the analysis target."
.state File Creation
This skill creates docs/analysis/.state on first run. Write initial state:
# Analysis State
classify-analysis-target: complete
Format: one line per skill, skill-name: complete | partial | blocked | skipped.
Every subsequent skill appends its status on completion.
Overview
Classify what we're analyzing before burning tokens. This skill determines target type, analysis feasibility, and applicable skills.
Process
- Scan top-level files: Look for manifest files (package.json, Cargo.toml, go.mod, requirements.txt, Dockerfile, .tf files, .csproj, pom.xml)
- Check file types:
find . -maxdepth 2 -type f | sed 's/.*\.//' | sort | uniq -c | sort -rn | head -20 - Detect obfuscation/minification: Check for single-line JS files, .pyc-only directories, .wasm files, packed binaries
- Identify repo structure: Single repo, monorepo (packages/ or workspaces/), multi-service (docker-compose)
- Classify target type and applicable skills
Target Types and Applicable Skills
| Target Type | Track A | Track B Phases |
|---|---|---|
| Web app (standard) | All 6 | All phases |
| Mobile (decompiled) | Tech stack only | All phases |
| IaC (Terraform/CF) | Tech stack + deps | Phase 2-3 (3 skills + 4 skills; no agent loop, no prompts) |
| Library/SDK | All 6 | If gated features found |
| Monorepo | All 6 | All phases |
| Container image | Tech stack only | All phases |
| Obfuscated/minified | BLOCK | Fail fast |
Note: All Track A skills emit SECURITY_SIGNAL in their output. These aggregate in the Track A summary for downstream security analysis.
Rationalization Table
| Excuse | Reality |
|---|---|
| "Looks like a standard web app" | Similar apps differ. Check manifests before assuming. |
| "I can skip this and just start analyzing" | Wrong skills produce garbage. 30 seconds saves hours. |
| "The user asked a specific question" | Specific questions still need classification to know WHERE to look. |
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 · 72 lines · 26 tokens per session scan A 9db65555e08a
classify-analysis-target is a skill published in the GitHub repository quangphu1912/codebase-analyzer (2 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 698 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.