codebase-second-brain

codebase-second-brain is a skill for Codex from Mallikarjun-Roddannavar/playwright-agentic-automation. It costs 72 tokens per session (2,696 once invoked), scanned A, original, MIT.

A persistent, searchable record of how a Playwright codebase is organized and how its features, tests, pages, services, and fixtures are related. A fixture is shared setup or test data used by tests.

In plain words
What is it for?
Use it to answer questions about feature behavior, test coverage, ownership, navigation, APIs, architecture, and stale or missing documentation.
Why use it?
It helps an agent discover the right files and verify whether documented architecture and behavior are current.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node ./scripts/buildKnowledge.mjs --check.

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Mallikarjun-Roddannavar/playwright-agentic-automation
agentmods
npx agentmods add skills/mallikarjun-roddannavar/playwright-agentic-automation/codebase-second-brain

Made for: Codex.

Wrote 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.

agentmods badge for codebase-second-brain

README.md
[![agentmods](https://agentmods.dev/badge/skills/mallikarjun-roddannavar/playwright-agentic-automation/codebase-second-brain.svg)](https://agentmods.dev/skills/mallikarjun-roddannavar/playwright-agentic-automation/codebase-second-brain)
Your own site
<a href="https://agentmods.dev/skills/mallikarjun-roddannavar/playwright-agentic-automation/codebase-second-brain"><img src="https://agentmods.dev/badge/skills/mallikarjun-roddannavar/playwright-agentic-automation/codebase-second-brain.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,696 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00072 $0.02696
Opus 5 $0.00036 $0.01348
Sonnet 5 $0.00014 $0.00539
Haiku 4.5 $0.00007 $0.00270

Measured 6d ago against content hash d43168cf4e62, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

codebase-second-brain 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 6d 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.

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.

.agents/skills/codebase-second-brain/SKILL.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codebase Second Brain

Use knowledge/ as the first discovery layer. It is a portable, offline-first OKF v0.2 bundle; generated/ contains deterministic AST facts and architecture/, decisions/, and runbooks/ hold durable human-readable knowledge.

Route Knowledge Questions Automatically

Use this skill as the primary skill for natural-language questions about:

  • how a feature works;
  • how product behavior maps to tests;
  • what tests, page objects, services, fixtures, or assertions cover a feature;
  • whether a documented behavior is stale, missing, or contradictory;
  • architecture, ownership, navigation, or API relationships.

Users should not need to name knowledge files, commands, or this skill. Start with the knowledge bundle, then use pw-ui-pom or pw-api-pom only as supporting context when the retrieved relationships point to UI or API implementation.

For a knowledge question, follow this order:

  1. Read knowledge/index.md and run the relevant freshness/validation check.
  2. Query the requested feature, symbol, route, or relationship.
  3. Open the returned knowledge notes and their direct evidence links.
  4. Inspect only the authoritative source lines needed to confirm an important claim or resolve a conflict; do not broadly rediscover the repository first.
  5. Report the answer naturally, separating known knowledge, source verification, runtime test results, and missing evidence.

If source and knowledge disagree, explicitly report STALE or CONFLICTED. Treat source as authoritative, but do not silently rewrite the knowledge bundle. VERIFIED knowledge evidence does not imply that a Playwright test was executed; report runtime execution separately.

When multiple endpoints, implementations, or authentication paths exist, trace the one actually used by the requested feature or test. Distinguish it from alternate supported endpoints. A route mentioned in a product note is not proof that the current UI or test uses that route; follow the concrete call site, service method, fixture, or graph relationship. If the note and call site differ, report the claim as STALE or CONFLICTED and explain which path is authoritative for the requested flow.

Read the full file on GitHub · 259 lines

Files

What ships with it

2 files 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.

Changes

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.

  1. 6d ago First seen · 259 lines · 72 tokens per session scan A d43168cf4e62

Subscribe to this mod's changes

codebase-second-brain is a skill published in the GitHub repository Mallikarjun-Roddannavar/playwright-agentic-automation (11 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 2,696 once invoked, about $0.0004 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.