CWC Workshops is a collection of materials from Anthropic-run workshops on building and evaluating AI-assisted coding workflows. The workshops cover model selection, multi-agent systems, managed agents, and product development with coding agents. The catalogue entries are examples and teaching materials from those workflows.
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 skills add anthropics/cwc-workshops --skill submit-solutiongit clone --depth 1 https://github.com/anthropics/cwc-workshopsWrote 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/anthropics/cwc-workshops/submit-solution)<a href="https://agentmods.dev/skills/anthropics/cwc-workshops/submit-solution"><img src="https://agentmods.dev/badge/skills/anthropics/cwc-workshops/submit-solution/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/anthropics/cwc-workshops/submit-solution"><img src="https://agentmods.dev/badge/skills/anthropics/cwc-workshops/submit-solution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.00725 |
| Opus 5.5 | $0.00020 | $0.00290 |
| Sonnet 5.5 | $0.00010 | $0.00145 |
| Haiku 4.5 | $0.00005 | $0.00072 |
Grade A, and why
submit-solution 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 1mo 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Submit your StockPilot solution
You're helping a workshop attendee package up their agents/starter/agent.py
decomposition and open a PR. The PR is how facilitators see what approaches
people took, and the description doubles as the workshop feedback form.
Step 1 — Ask about their experience first
Before touching git, ask these three questions (use AskUserQuestion or just conversational):
- Which subagent approach did you go with for cycle 3? (callable_agents / spawn_subagent / inline / something else)
- What was the hardest part of the workshop? (a specific cycle, a concept, the tooling, the timing)
- One thing you'd change about it?
Hold onto their answers — they go in the PR body.
Step 2 — Show them what they're submitting
git diff main -- agent-decomposition/agents/starter/agent.py
Walk through the diff briefly: which tools they dropped, which skills they enabled, which subagent approach they wired. If the diff is empty, they haven't edited starter — ask if they worked in a different file.
Also grab their final eval score:
ls -t evals/reports/*/starter.json | head -1 | xargs cat | python -c "import json,sys; d=json.load(sys.stdin); print(f'{d[\"score\"]:.0%}')"
Step 3 — Commit and push
git checkout -b solution/<their-name-or-handle>
git add agent-decomposition/agents/starter/agent.py
git commit -m "Workshop solution: <subagent approach>, <score>%"
git push -u origin solution/<their-name-or-handle>
Ask for their name/handle if you don't have it. If they don't have push
rights to anthropics/cwc-workshops, have them fork first
(gh repo fork --clone=false) and push to their fork.
Step 4 — Open the PR with feedback in the body
gh pr create --title "Workshop solution — <name>" --body-file -
PR body template (fill from step 1 + step 2):
## My decomposition
- Subagent approach: <callable_agents | spawn_subagent | inline | other>
- Final eval score: <NN>%
- Tools I dropped: <list>
- Skills I enabled: <list>
## Workshop feedback
**Hardest part:** <their answer>
**One thing I'd change:** <their answer>
**Anything else:** <free text — leave blank if nothing>
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.
- 1mo ago First seen · 92 lines · 50 tokens per session scan A 26e9a8668869
submit-solution is a skill published in the GitHub repository anthropics/cwc-workshops (2,210 stars, last pushed 6d ago), licensed Apache-2.0. It adds 50 tokens to every session and 725 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.