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/inventorying-api-surfacenpx skills add quangphu1912/codebase-analyzer --skill inventorying-api-surfacegit 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 | $0.00028 | $0.01202 |
| Opus 5 | $0.00014 | $0.00601 |
| Sonnet 5 | $0.00006 | $0.00240 |
| Haiku 4.5 | $0.00003 | $0.00120 |
Grade A, and why
inventorying-api-surface 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 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **IPC channels**: `ipcMain.handle`, `ipcRenderer.send`, Electron/Node child_process message protocols How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Announce at start: "Using codebase-analyzer to inventory the API surface."
Overview
Catalog every public interface: exported functions, classes, types, REST/GraphQL endpoints, and their contracts. This skill finds implicit ENTRY POINTS (how you get in: undocumented endpoints, conditionally exposed routes, IPC channels, WebSocket message types, CLI argument schemas, environment variable contracts, plugin hooks). For implicit BEHAVIORAL ASSUMPTIONS (how code expects to be used), use detect-hidden-contracts.
Process
- Find public exports (export, module.exports, pub fn, def with all)
- Map REST/GraphQL/RPC endpoints if applicable
- Document function signatures and type contracts
- Find breaking change risks (widely-used public APIs)
- Find undocumented public APIs
- Categorize by stability: stable, experimental, deprecated, internal-but-exported
- Map implicit entry points beyond HTTP (see Implicit Entry Points below)
- Trace API-to-data-flow: verify every endpoint touches data, detect endpoint chains
API-to-Data-Flow Mapping
Every endpoint should be traceable to a data mutation or query. Endpoints that don't touch data are either proxies, health checks, or dead endpoints.
Chain detection: if endpoint A's response shape matches endpoint B's request body, they are designed to be chained. That reveals intended workflows the codebase expects but may never document. Look for:
- Response schemas that mirror request schemas on other endpoints
- IDs returned from create endpoints that feed directly into detail endpoints
- Pagination cursors that flow into subsequent calls
- Field names that are identical across request/response boundaries
Implicit Entry Points
Not just HTTP: the implicit API is often larger than the explicit one. Check for:
- IPC channels:
ipcMain.handle,ipcRenderer.send, Electron/Node child_process message protocols - WebSocket message types: JSON message discriminators (
typefield), subscription channels - CLI argument schemas: argparse/click/ commander definitions, each flag is an API contract
- Environment variable contracts:
process.env.Xreads that control behavior without being documented as config - Plugin hooks: extension points, event emitters, middleware registration functions, lifecycle callbacks
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.
- 2d ago First seen · 88 lines · 28 tokens per session scan A 9e84bd88278a
inventorying-api-surface is a skill published in the GitHub repository quangphu1912/codebase-analyzer (2 stars, last pushed 4mo ago), licensed MIT. It adds 28 tokens to every session and 1,202 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…