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/kolodkin/devpowers/local-docker-debugnpx skills add kolodkin/devpowers --skill local-docker-debuggit clone --depth 1 https://github.com/kolodkin/devpowersWhat 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 | $0.00068 | $0.00986 |
| Opus 5 | $0.00034 | $0.00493 |
| Sonnet 5 | $0.00014 | $0.00197 |
| Haiku 4.5 | $0.00007 | $0.00099 |
Grade A, and why
local-docker-debug scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `curl` for connectivity checks against services the user explicitly asks about How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local Docker Debugging
Discover and tail logs for Docker containers running on the local Docker daemon.
Arguments
/local-docker-debug [container-name ...]
- container-name (optional, repeatable) — One or more container names or IDs to tail. If omitted, run the discovery phase and ask the user which containers to tail.
IMPORTANT
This skill is strictly read-only on the local Docker daemon. NEVER run docker exec, docker build, docker compose up/down, docker run, docker rm, docker stop, docker restart, or any command that modifies container or host state. Only the following are allowed:
docker ps(and variants with--format,-a,--filter)docker logs(with--tail,--since,-f)docker inspect(read-only metadata)curlfor connectivity checks against services the user explicitly asks about
If the user asks for anything that would mutate state, refuse and explain that this skill is read-only.
Step 1: Discovery Phase
Run when no container names were supplied, or when the user explicitly asks "what's running" / "list containers" / similar.
List running containers with a clean, parseable format:
docker ps --format 'table {{.Names}}\t{{.Image}}\t{{.Status}}\t{{.Ports}}'
To include stopped containers as well, add -a:
docker ps -a --format 'table {{.Names}}\t{{.Image}}\t{{.Status}}'
Present the list to the user and ask which containers they'd like to tail. If there are obvious candidates based on the user's stated goal (e.g. they mentioned a service name that matches a container), suggest those by name.
Step 2: Tail Logs
For each container the user selected (or supplied as arguments), start a background log stream. Launch all streams in parallel:
docker logs -f --tail 1000 <container-name> 2>&1
# Run with run_in_background: true
Repeat one invocation per container. Tell the user which streams are running and that you'll check them as needed.
Use Read on the background output files to inspect logs during the session. When the user describes a symptom, grep through the captured output rather than re-tailing.
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 · 96 lines · 68 tokens per session scan A 06bd9b21d11f
local-docker-debug is a skill published in the GitHub repository kolodkin/devpowers (2 stars, last pushed 23d ago), licensed MIT. It adds 68 tokens to every session and 986 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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…