Watch upstream
Fetch official Anthropic/Claude Code docs, detect changes relevant to dotforge, report deltas.From its SKILL.md
npx -y skills add luiseiman/dotforge --skill watch-upstreamAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 8 stars8 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
4.0 KB, 995 tokens by cl100k_base, as published. Nobody here has run it
Watch Upstream
Detect changes in official Claude Code documentation that may require updates to dotforge.
Step 0: Discover tools
WebFetch and WebSearch are deferred tools — they may not be loaded yet.
Run ToolSearch("WebFetch WebSearch") to ensure both tools are available before proceeding.
If either tool is not found, fall back to Bash(curl -s <url>) for fetching.
Step 1: Fetch current documentation
Use WebFetch to read these pages directly:
https://code.claude.com/docs/en/overview— main feature listhttps://code.claude.com/docs/en/settings— settings.json schema, permissionshttps://code.claude.com/docs/en/hooks— hook types, events, matchershttps://code.claude.com/docs/en/memory— memory and context managementhttps://code.claude.com/docs/en/sub-agents— subagent capabilities (renamed from agent-tool)https://code.claude.com/docs/en/cli— CLI flags and options
If any URL fails, use WebSearch with query "Claude Code" <topic> site:code.claude.com as fallback.
If a URL returns 404 instead of redirecting, fall back to https://code.claude.com/docs/llms.txt (canonical index) and search for the slug — the new domain reorganized some paths (e.g. agent-tool → sub-agents).
Then search for recent announcements:
- WebSearch:
Claude Code new features 2026 - WebSearch:
Claude Code changelog site:anthropic.com - WebSearch:
Claude Code hooks settings update site:github.com/anthropics
Step 2: Extract and classify changes
For each finding, check if it affects dotforge:
| What to look for | Where it impacts dotforge |
|---|---|
| New hook event types (beyond PreToolUse/PostToolUse/Stop) | template/hooks/, stacks/*/hooks/ |
| New settings.json fields or changed schema | template/settings.json.tmpl, global/settings.json.tmpl |
| New permission categories | stacks/*/settings.json.partial |
| Changed deny list behavior | template/settings.json.tmpl deny section |
| New agent/subagent capabilities | agents/*.md |
| New skill/command system features | skills/*/SKILL.md |
| Deprecated features or breaking changes | Any affected file |
| New CLI flags relevant to automation | skills/benchmark/SKILL.md (uses claude --print) |
| MCP server changes | global/settings.json.tmpl |
Ignore: pricing, model releases (unless affecting tool use), marketing.
Step 3: Compare against dotforge
For each relevant finding, check the current state:
# Search template for existing coverage
grep -r "<keyword>" template/ stacks/ global/ agents/ skills/
Classify each finding:
- Gap: dotforge doesn't cover this at all
- Partial: dotforge covers this but is outdated or incomplete
- Covered: dotforge already handles this correctly
- Breaking: dotforge does something that conflicts with the new behavior
Step 4: Report
═══ WATCH UPSTREAM ═══
Date: {{YYYY-MM-DD}}
Sources fetched: {{N}} docs, {{N}} search results
── CHANGES DETECTED ──
🆕 NEW: {{title}}
Source: {{url}}
Impact: {{which dotforge files would change}}
Priority: {{high|medium|low}}
⚠️ BREAKING: {{title}}
Source: {{url}}
Current dotforge behavior: {{what we do now}}
Required change: {{what needs to change}}
📝 PARTIAL: {{title}}
Source: {{url}}
What's covered: {{existing coverage}}
What's missing: {{gap}}
── SUMMARY ──
Gaps: {{N}} | Partial: {{N}} | Breaking: {{N}} | Covered: {{N}}
── NEXT STEPS ──
For each gap/partial/breaking, run:
/forge capture "{{description}}"
Then: /forge update to evaluate and incorporate.
Constraints
- DO NOT modify any dotforge files. Report only.
- DO NOT auto-create practices. Suggest
/forge capturecommands for the user. - If web fetch fails, report clearly — don't guess or hallucinate features.
- If no changes detected, report "No relevant changes found" — this is a valid outcome.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most docs writing skills give in 995 tokens
Counted across 1,951 of the 3,904 authors here whose files we hold, read 2026-09-06
- Use third-person for skill descriptionsin 54 of 1951, across 35 files
- Start descriptions with Use whenin 43 of 1951, across 29 files
- Run baseline scenarios before writing any skillin 40 of 1951, across 26 files
- Use active voicein 40 of 1951, across 36 files
- Map file responsibilities before defining tasksin 36 of 1951, across 29 files
- Use checkbox syntax for tracking stepsin 35 of 1951, across 27 files
- Ask one question at a timein 35 of 1951
- Offer execution options after saving the planin 33 of 1951, across 24 files
- Include complete code in every stepin 33 of 1951, across 27 files
- Design units with clear boundaries and interfacesin 31 of 1951, across 23 files
- Announce the skill usage at the startin 30 of 1951
- Verify agent compliance after adding the skillin 29 of 1951, across 17 files
Said here and by no other author read
- Run ToolSearch to ensure WebFetch and WebSearch are available
- Search for recent announcements and changelogs
- Classify changes based on impact to project files
- Classify findings as Gap, Partial, Covered, or Breaking
- Suggest forge capture commands for identified changes
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.