Please comment if you see anything wrong or ways these can be improved!

LiteLLM: find / \( -type d -name "litellm-.dist-info" -o -name "litellm_init.pth" \) 2>/dev/null \ | while read d; do case "$d" in dist-info) v=$(echo "$d" | sed 's/.litellm-\(.\)\.dist-info/\1/') if echo "$v" | grep -qE '^1\.82\.(7|8)$'; then echo "COMPROMISED: $d -> litellm $v" else echo "CLEAN: $d -> litellm $v" fi ;; pth) echo "COMPROMISED: malicious .pth file found at $d" ;; esac done

Example output: CLEAN: /System/Volumes/Data/Users/johndamask/code/my-own-agents-shove-it/openai-agents-sdk/thebostonwrongs/.venv/lib/python3.12/site-packages/litellm-1.67.5.dist-info -> litellm 1.67.5 CLEAN: /System/Volumes/Data/Users/johndamask/code/ai-evals-course/recipe-chatbot-langchain/.venv/lib/python3.12/site-packages/litellm-1.78.5.dist-info -> litellm 1.78.5 CLEAN: /System/Volumes/Data/Users/johndamask/code/ai-evals-course/recipe-chatbot/.venv/lib/python3.12/site-packages/litellm-1.73.6.dist-info -> litellm 1.73.6

Axios: find . -path "/node_modules/axios/package.json" 2>/dev/null \ | while read f; do v=$(grep '"version"' "$f" | head -1 | sed 's/.: "\(.\)"./\1/') dir=$(dirname "$f") if echo "$v" | grep -qE '^(1\.14\.1|0\.30\.4)$'; then echo "COMPROMISED: $dir -> axios $v" else echo "CLEAN: $dir -> axios $v" fi done

Comments URL: https://news.ycombinator.com/item?id=47614201

Points: 1

# Comments: 0

From the description: Create a token-secured REST API endpoint backed by AWS Lambda and DynamoDB with full CRUD and paginated list support. Deploys via CloudFormation. Use when user wants to quickly spin up an API endpoint, create a simple REST API on AWS, build a quick data store with an API, set up a Lambda+DynamoDB endpoint, or needs a fast way to log and retrieve structured data. Triggers on "create an endpoint", "quick API", "Lambda endpoint", "DynamoDB API", "CRUD endpoint", "log data to AWS".

Example use: Thariq's recent post on how the team uses Claude Skills has a section on logging skill use with a PreToolUse hook (https://x.com/trq212/status/2033949937936085378). His example code shows logging to a local file but for company-wide tracking, you'd want to log to a central place. I used my skill to stand up an endpoint for this and my ~/.claude/hooks/log-skill.sh POSTS to it:

skill=$(echo "$prompt" | awk '{print $1}' | sed 's|^/||') args=$(echo "$prompt" | sed 's|^/[^ ]||' | sed 's|^ ||')

# Build the JSON body body=$(jq -nc \ --arg skill_name "$skill" \ --arg invoked_by "$USER" \ --arg args "$args" \ --arg session_id "$session_id" \ '{skill_name: $skill_name, invoked_by: $invoked_by, args: $args, session_id: $session_id}')

# POST to the endpoint (fire-and-forget so we don't block the prompt) curl -sf -X POST "$ENDPOINT" \ -H "Content-Type: application/json" \ -H "x-api-token: ${SKILL_LOG_TOKEN}" \ -d "$body" \ >/dev/null 2>&1 &

Comments URL: https://news.ycombinator.com/item?id=47445554

Points: 1

# Comments: 0

I use it in interactive Claude Code sessions. For example, if I want to add a Claude API feature to an app, I'll often hack it together first in CC. This skill lets me start and stop tracking so I get get a sense for what the API costs will be.

For example:

> /cost-tracking > [do stuff] > stop tracking

Then I get a nice little table showing tokens and cost for the model that was used:

Haiku cost report (this session's work):

  ┌───────────────────┬───────────┬─────────┐
  │     Category      │  Tokens   │  Cost   │
  ├───────────────────┼───────────┼─────────┤
  │ Base input        │ 182       │ $0.0002 │
  ├───────────────────┼───────────┼─────────┤
  │ Output            │ 3,276     │ $0.0164 │
  ├───────────────────┼───────────┼─────────┤
  │ Cache writes (1h) │ 25,619    │ $0.0512 │
  ├───────────────────┼───────────┼─────────┤
  │ Cache reads       │ 1,585,531 │ $0.1586 │
  ├───────────────────┼───────────┼─────────┤
  │ Grand Total       │           │ $0.2264 │
  └───────────────────┴───────────┴─────────┘

Comments URL: https://news.ycombinator.com/item?id=47299439

Points: 2

# Comments: 0

1) Modes. You can now choose between Native, Non-Technical, or Kid-Friendly mode. Here are results for the same paper Native: https://test.nowigetit.us/pages/62ef3639-02f0-472b-b0a6-79f6... Non-technical: https://test.nowigetit.us/pages/eba32173-269f-4b5c-9df1-c782... Kid-friendly: https://nowigetit.us/pages/3c413c94-d843-4e84-8805-22af16021...

2) I'm working on user accounts with private galleries

3) Getting closer to opening this up with a cost-plus pricing model. Hopefully by next week but we'll see.

I also really like Claude's planning mode, except for the fact that it's tightly coupled with execution.

A pattern I've found is to work in different loops: a planning loop and an execution loop.

Planning loop: 1. Use GitHub issues for backlog items. Whenever I get an idea, I just make an issue with minimal detail. 2. Pull issue into Claude Code 3. Create branch 4. Use a home-grown planning skill that reads the Issue and operates pretty much the same way as Claude's but without the straight-to-execution annoyance 5. Once the plan is finalized, decompose it into Beads 6. Check in branch and tag as "ready"

Execution loop: Watch GitHub for "ready" issues. When one is found, checkout a worktree then start building. All the beads are self-contained in the issue so there's no need for more discussion with the LLM.

I turned the planning phase into a Claude plugin that I can invoke with a slash command, /beads-planner issue 44. The execution loop can be ralph or even just interactive CC sessions.

Everyone is coming up with their own way to build but figured I'd share because this works for me. YMMV

Comments URL: https://news.ycombinator.com/item?id=47263696

Points: 1

# Comments: 0

I'm considering some ways to direct the LLM but we're in this funny period where models are getting better on subjective things like look-and-feel. And if I direct too much, I may wind up over-fitting for today's models.

I haven't done any token/cost optimization so far because a) the app works well-enough for me, personally; b) I need more data to understand the areas to optimize.

Most likely, I'd start with quality optimizations that matter to users. Things to make people happier with the results.