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.
git clone --depth 1 https://github.com/Mallikarjun-Roddannavar/playwright-agentic-automationnpx agentmods add skills/mallikarjun-roddannavar/playwright-agentic-automation/codebase-second-brainWrote 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.
[](https://agentmods.dev/skills/mallikarjun-roddannavar/playwright-agentic-automation/codebase-second-brain)<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>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.
| Model | Per session | Once 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 |
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.
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:
- Read
knowledge/index.mdand run the relevant freshness/validation check. - Query the requested feature, symbol, route, or relationship.
- Open the returned knowledge notes and their direct evidence links.
- Inspect only the authoritative source lines needed to confirm an important claim or resolve a conflict; do not broadly rediscover the repository first.
- 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.
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.
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.
- 6d ago First seen · 259 lines · 72 tokens per session scan A d43168cf4e62
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.
Other skills, from other repositories
update-setup
One-time setup wizard for the memmy upgrade skill. Triggers: setup update, configure update, 切设置更新, 初始化更新.
skill-creator
Create, edit, improve, tidy, review, audit, or restructure memmy-agent skills and SKILL.md files.
memmy-memory
Use the shared Memmy memory service to retrieve relevant prior context and persist durable Agent turns, facts, decisions, preferences, procedures, and follow-ups.
ui-craft
Design, build, redesign, or modify browser-visible web interfaces with product-quality composition, visual systems, interaction states, responsive behavior, accessibility, and browser visual QA. Use for HTML, CSS, JavaScript, React, Vue, or Svelte pages and components, landing pages, dashboards, admin tools, settings…
memmy-memory
Use the memmy-memory CLI when an agent needs to check the Memory service, open or close agent sessions, start or complete turns, search, add, read, or delete memories, or call uncommon HTTP routes through raw requests.
agentlas-auto-activation
Use when adding or auditing local runtime behavior that turns a project folder into an Agentlas-aware workspace with .agentlas memory and sitemap files.