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-data-flowsnpx skills add quangphu1912/codebase-analyzer --skill trace-data-flowsgit 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 | $0.00037 | $0.01705 |
| Opus 5 | $0.00018 | $0.00852 |
| Sonnet 5 | $0.00007 | $0.00341 |
| Haiku 4.5 | $0.00004 | $0.00170 |
Grade A, and why
trace-data-flows 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using codebase-analyzer to trace data flows.
Overview
Follow the data, not the code. Code shows structure; data shows behavior. Where does untrusted data enter? Where is it validated? Where does it influence control flow? Where does it persist? Where does it exit?
Every bug is data taking an unexpected path. Every vulnerability is data reaching a dangerous destination without proper clearance.
Prerequisites
Read these files first for context:
docs/analysis/tech-stack.md— framework conventions for data handlingdocs/analysis/build-pipeline.md— build-time vs runtime data boundaries
Five-Stage Data Flow Trace
1. Entry — Where Does External Data Arrive?
Map every point where data crosses the system boundary:
- HTTP parameters — query strings, headers, cookies, request bodies (JSON/form)
- File uploads — multipart data, file paths from user input
- Environment variables — configuration injected at runtime
- IPC / message queues — data from other services, event streams, pub/sub
- Database reads — data previously stored may have been poisoned
- API responses — third-party data is untrusted by definition
For each entry point, record: the source, the data shape expected, and the trust level assigned.
2. Validation — Where Is Data Checked?
If at all. Gaps between entry and usage are injection risks.
Search for:
- Schema validation (Zod, Joi, Pydantic, protobuf, JSON Schema)
- Input sanitization (escaping, trimming, type coercion)
- Allowlist validation (enum checks, regex patterns)
- Authorization checks (can this user access this data?)
Critical: Note every entry point that has NO corresponding validation before the data is used. These are vulnerabilities.
3. Control Flow — Where Does Data Influence Execution?
This is where injection lives. When untrusted data determines what code runs:
- SQL queries — string interpolation, concatenation in query building
- Shell commands — data passed to
exec(),system(), backtick operators - Template rendering — data injected into HTML (XSS), templates (SSTI)
- Dynamic dispatch — data used as function names, class names, file paths
- Configuration — data that alters application behavior (feature flags, routing)
- Deserialization — data decoded into objects (pickle, YAML.load, unserialize)
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 · 177 lines · 37 tokens per session scan A 84736ad8d15f
trace-data-flows is a skill published in the GitHub repository quangphu1912/codebase-analyzer (2 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 1,705 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…