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/trace-codebase-provenancenpx skills add quangphu1912/codebase-analyzer --skill trace-codebase-provenancegit 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 | $0.00039 | $0.00844 |
| Opus 5 | $0.00019 | $0.00422 |
| Sonnet 5 | $0.00008 | $0.00169 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade A, and why
trace-codebase-provenance 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Announce at start: "Using codebase-analyzer to trace codebase provenance."
Overview
Distinguish source of truth from derived layers. Critical first step — if you misidentify generated code as source, every downstream analysis is poisoned.
Prerequisite: Reads docs/analysis/target-classification.md and docs/analysis/tech-stack.md.
Deception Awareness
Assume the codebase may be trying to hide things. Look for: deliberately misleading variable names, code structured to look like one thing but do another, comments describing intent that doesn't match implementation, obfuscated strings, encoded URLs.
Intent-Implementation Gap
Comments say "validates user input" but the function only trims whitespace. Function named sanitize that passes data through unchanged. The gap between stated purpose and actual behavior is where the truth lives. Always verify what code DOES, not what it SAYS it does.
Process
- Check for sourcemap files (*.map, .js.map) — if present without corresponding source, this is derived
- Look for compilation markers: "DO NOT EDIT", "@generated", timestamps in headers
- Identify hand-written vs machine-generated code patterns (see references/provenance-patterns.md)
- Check git history: were files committed in batches (generated) or individually (hand-written)?
- Scan for deception indicators: misleading names, intent-implementation gaps, obfuscated sections
- Identify the source-of-truth layer: where did this code originate?
- Map derivation chain: source -> intermediate -> shipped -> runtime
- Produce provenance map with build dimension catalogue
The Iron Law
Never confuse sourcemap with source, build output with source, decompiled code with original code.
Build Dimension Catalogue
Every analysis output MUST include which config axes were examined:
## Build Dimensions Analyzed
- ENVIRONMENT: development (current)
- USER_TYPE: external (assumed from build)
- PROVIDER: not determined
## Dimensions NOT Analyzed
- USER_TYPE: internal, admin
- PROVIDER: all variants
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.
- yesterday First seen · 91 lines · 39 tokens per session scan A dfe3c06dd6a3
trace-codebase-provenance is a skill published in the GitHub repository quangphu1912/codebase-analyzer (2 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 844 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…