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/mitodl/agent-kit/screenshot-prnpx skills add mitodl/agent-kit --skill screenshot-prgit clone --depth 1 https://github.com/mitodl/agent-kitWhat 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 | $0.00092 | $0.03393 |
| Opus 5 | $0.00046 | $0.01697 |
| Sonnet 5 | $0.00018 | $0.00679 |
| Haiku 4.5 | $0.00009 | $0.00339 |
Grade A, and why
screenshot-pr scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -o /dev/null -w "%{http_code} localhost:$port\n" --max-time 1 "http://localhost:$port/" 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screenshot PR Changes
Capture UI changes for a pull request across three standard viewports using shot-scraper.
Requires: shot-scraper available on PATH (it is a system-level utility, not a per-project dependency — do not install it with uv or pip inside the project).
Check it is present before proceeding:
which shot-scraper && shot-scraper --version
If the command is missing, ask the user to install it globally (e.g. uv tool install shot-scraper --global, pipx install shot-scraper, or their preferred method) and confirm Chromium is available (shot-scraper install). Do not install it yourself.
Step 0 — Discover the base URL
Run these checks in order and stop at the first hit:
a) Check .env (or .env.local) in the repo root:
grep -E "(BASE_URL|SITE_URL|APP_URL)" .env .env.local 2>/dev/null | head -10
Look for vars like MITX_ONLINE_BASE_URL, SITE_URL, NEXT_PUBLIC_BASE_URL.
b) Check docker-compose.yml for env defaults:
grep -E "(BASE_URL|APISIX_PORT|_PORT)" docker-compose.yml 2>/dev/null | head -20
Pay attention to APISIX_PORT (default 9080) — screenshots of authenticated
pages must go through the APISIX port, not the raw app port, so session
cookies work. If the app hostname is api.open.odl.local and APISIX is at
8065, the base URL for screenshots is http://api.open.odl.local:8065.
c) Probe common ports for a live server:
for port in 9080 3000 5173 8000 8013; do
curl -s -o /dev/null -w "%{http_code} localhost:$port\n" --max-time 1 "http://localhost:$port/" 2>/dev/null
done
d) Check the README or session context for any URLs mentioned.
Record two values: base_url (used for all screenshot URLs) and login_url
(<base_url>/login, used for auth). If nothing is found, ask the user.
Step 1 — Establish an auth context
Authentication in this dev stack flows through APISIX → Keycloak. The
shot-scraper --auth flag takes a Playwright storage-state JSON file; this
step generates or reuses one.
What ships with it
1 file 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.
- 2d ago First seen · 364 lines · 92 tokens per session scan A e862c3f75124
screenshot-pr is a skill published in the GitHub repository mitodl/agent-kit (2 stars, last pushed 4d ago), licensed BSD-3-Clause. It adds 92 tokens to every session and 3,393 once invoked, about $0.0005 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…