privacy
claudeRefuses a shell, file, web fetch or MCP call that holds the signed-in account's email address beside a word that declares who is calling, so the address does not go out as a client's identity.
Cocoonstack code standards: /code, /code-rs, /code-py, /code-ts, /review-round and /loc-justify skills with the asl commit gate
Plugin cocoon-code-standards from marketplace asl-marketplace in CMGS/asl. Commands read from the repo's manifest — yesterday.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
code-pyPython code review & refactor standard for cocoonstack projects — the Python counterpart to /code (Go) and /code-rs (Rust). Load for any Python code work in cocoonstack repos; subagents read files in full, the session model adjudicates and runs the final Style Self-Check on every touched file.
code-rsCocoon code style standards for Rust projects — module/declaration layout, use-grouping (std/external/crate), comment minimalism, error handling (Result + context, no unwrap in non-test), ownership/borrow discipline (no gratuitous clones), unsafe isolation, async/tokio discipline, naming, cargo/CI c
code-tsTypeScript/React code review & refactor standard for cocoonstack projects — the TS counterpart to /code (Go), /code-rs (Rust) and /code-py (Python). Load for any TypeScript or React work in cocoonstack repos; subagents read files in full, the session model adjudicates and runs the final Style Self-C
codeCocoon code style standards for Go projects — declaration layout (single top-of-file const/var block), test-file layout (tests before helpers), signature naming (named constraints and func types), hard comment budget (STE 101 register), mandatory modern Go (the use-modern-go catalog for the go.mod v
loc-justifyWhole-repo production-code (non-test) volume audit — measure prod LOC composition and growth with exact commands, attribute it to packages/commits/buckets, then force an item-by-item justify verdict (EARNED / CHALLENGED with a ranked cut-list) via multi-agent lenses and adversarial verification. Rep
review-roundThe cocoonstack batch-end quality convergence loop — style walkthroughs per /code, /code-rs, /code-py and /code-ts (subagents read files in full, Fable adjudicates and runs the final Self-Check), multi-agent correctness review with model tiering, flow readers over crash windows, /simplify lenses, co
bash "${CLAUDE_PLUGIN_ROOT}/hooks/asl-gate.sh"
Refuses a shell, file, web fetch or MCP call that holds the signed-in account's email address beside a word that declares who is calling, so the address does not go out as a client's identity.
Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.
1 skill
Generate natively editable PPTX from PDF / DOCX / URL / Markdown — real DrawingML shapes, text boxes, charts, and animations. Note: run `pip install -r requirements.txt` inside the installed plugin directory for the Python post-processing scripts to work.
1 skill
Install the "AAS Python Development" editorial skill bundle for Claude Code.
13 skills
Web scraping, Google search, structured data extraction, and MCP server integration powered by Bright Data. Includes 7 skills: scrape any webpage as markdown (with bot detection/CAPTCHA bypass), search Google with structured JSON results, extract data from 40+ websites (Amazon, LinkedIn, Instagram, TikTok, YouTube, and more), orchestrate Bright Data's 60+ MCP tools, built-in best practices for Web Unlocker, SERP API, Web Scraper API, and Browser API, Python SDK best practices for the brightda...
21 skills
Modern Python development with Python 3.12+, Django, FastAPI, async patterns, and production best practices
16 skills · 1 command · 3 agents
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.