agentrigs
+ submit rig
~ / rigs / sefaertunc / anthropic-watch

sefaertunc/anthropic-watch

Monitors 37 Anthropic sources daily and publishes structured RSS/JSON feeds: upstream intelligence for Claude Code

↗ GitHub ★ 1 MIT updated today project Claude CodeCodex
share on X
ARCHETYPE
Fort Knox
Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.
CONTEXT TAX · EVERY TURN
~5.6k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
4/5
Blocks destructive commands · Protects secrets · No YOLO mode · Sandbox or ask-first rules · details

Copy this rig

# review before running: this installs third-party code
$ claude mcp add --transport http socket-mcp https://mcp.socket.dev/
$ npx degit sefaertunc/anthropic-watch/.claude ./rig-anthropic-watch  # inspect, then merge into .claude/

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ claude mcp add --transport http socket-mcp https://mcp.socket.dev/
$ npx degit sefaertunc/anthropic-watch/.claude/skills/agent-routing .claude/skills/agent-routing
$ npx degit sefaertunc/anthropic-watch/.claude/skills/backend-conventions .claude/skills/backend-conventions
$ npx degit sefaertunc/anthropic-watch/.claude/skills/claude-md-maintenance .claude/skills/claude-md-maintenance
$ npx degit sefaertunc/anthropic-watch/.claude/skills/coding-principles .claude/skills/coding-principles
$ npx degit sefaertunc/anthropic-watch/.claude/skills/context-management .claude/skills/context-management
$ npx degit sefaertunc/anthropic-watch/.claude/skills/coordinator-mode .claude/skills/coordinator-mode
$ npx degit sefaertunc/anthropic-watch/.claude/skills/frontend-design-system .claude/skills/frontend-design-system
$ npx degit sefaertunc/anthropic-watch/.claude/skills/git-conventions .claude/skills/git-conventions
$ npx degit sefaertunc/anthropic-watch/.claude/skills/memory-architecture .claude/skills/memory-architecture
$ npx degit sefaertunc/anthropic-watch/.claude/skills/planning-with-files .claude/skills/planning-with-files
$ npx degit sefaertunc/anthropic-watch/.claude/skills/project-patterns .claude/skills/project-patterns
$ npx degit sefaertunc/anthropic-watch/.claude/skills/prompt-engineering .claude/skills/prompt-engineering
$ npx degit sefaertunc/anthropic-watch/.claude/skills/review-and-handoff .claude/skills/review-and-handoff
$ npx degit sefaertunc/anthropic-watch/.claude/skills/security-checklist .claude/skills/security-checklist
$ npx degit sefaertunc/anthropic-watch/.claude/skills/subagent-usage .claude/skills/subagent-usage
$ npx degit sefaertunc/anthropic-watch/.claude/skills/testing .claude/skills/testing
$ npx degit sefaertunc/anthropic-watch/.claude/skills/verification .claude/skills/verification
$ curl -fsSL --create-dirs -o .claude/agents/bug-fixer.md https://raw.githubusercontent.com/sefaertunc/anthropic-watch/main/.claude/agents/bug-fixer.md
$ curl -fsSL --create-dirs -o .claude/agents/build-fixer.md https://raw.githubusercontent.com/sefaertunc/anthropic-watch/main/.claude/agents/build-fixer.md
$ curl -fsSL --create-dirs -o .claude/agents/build-validator.md https://raw.githubusercontent.com/sefaertunc/anthropic-watch/main/.claude/agents/build-validator.md
$ curl -fsSL --create-dirs -o .claude/agents/changelog-generator.md https://raw.githubusercontent.com/sefaertunc/anthropic-watch/main/.claude/agents/changelog-generator.md
$ curl -fsSL --create-dirs -o .claude/agents/ci-fixer.md https://raw.githubusercontent.com/sefaertunc/anthropic-watch/main/.claude/agents/ci-fixer.md
$ curl -fsSL --create-dirs -o .claude/agents/code-simplifier.md https://raw.githubusercontent.com/sefaertunc/anthropic-watch/main/.claude/agents/code-simplifier.md
$ curl -fsSL --create-dirs -o .claude/agents/dependency-manager.md https://raw.githubusercontent.com/sefaertunc/anthropic-watch/main/.claude/agents/dependency-manager.md
$ curl -fsSL --create-dirs -o .claude/agents/deploy-validator.md https://raw.githubusercontent.com/sefaertunc/anthropic-watch/main/.claude/agents/deploy-validator.md
$ curl -fsSL --create-dirs -o .claude/agents/doc-writer.md https://raw.githubusercontent.com/sefaertunc/anthropic-watch/main/.claude/agents/doc-writer.md
$ curl -fsSL --create-dirs -o .claude/agents/docker-helper.md https://raw.githubusercontent.com/sefaertunc/anthropic-watch/main/.claude/agents/docker-helper.md
$ curl -fsSL --create-dirs -o .claude/agents/e2e-runner.md https://raw.githubusercontent.com/sefaertunc/anthropic-watch/main/.claude/agents/e2e-runner.md
$ curl -fsSL --create-dirs -o .claude/agents/performance-auditor.md https://raw.githubusercontent.com/sefaertunc/anthropic-watch/main/.claude/agents/performance-auditor.md
$ curl -fsSL --create-dirs -o .claude/agents/plan-reviewer.md https://raw.githubusercontent.com/sefaertunc/anthropic-watch/main/.claude/agents/plan-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/refactorer.md https://raw.githubusercontent.com/sefaertunc/anthropic-watch/main/.claude/agents/refactorer.md
$ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/sefaertunc/anthropic-watch/main/.claude/agents/security-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/test-writer.md https://raw.githubusercontent.com/sefaertunc/anthropic-watch/main/.claude/agents/test-writer.md
$ curl -fsSL --create-dirs -o .claude/agents/upstream-watcher.md https://raw.githubusercontent.com/sefaertunc/anthropic-watch/main/.claude/agents/upstream-watcher.md
$ curl -fsSL --create-dirs -o .claude/agents/verify-app.md https://raw.githubusercontent.com/sefaertunc/anthropic-watch/main/.claude/agents/verify-app.md

Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.

{
  "permissions": {
    "deny": [
      "// -- Secret files (Read/Edit — Claude's own tools) --",
      "Read(./.env)",
      "Read(./.env.*)",
      "Read(./secrets/**)",
      "Edit(./.env)",
      "Edit(./.env.*)",
      "Edit(./secrets/**)",
      "Read(./*.pem)",
      "Read(./*.key)",
      "Read(./id_rsa)",
      "Read(./id_ed25519)",
      "// -- SSH and cloud creds (home-relative) --",
      "Read(~/.ssh/**)",
      "Read(~/.aws/credentials)",
      "Read(~/.config/gh/hosts.yml)",
      "// -- Bash file-view commands targeting .env --",
      "Bash(cat *.env*)",
      "Bash(head *.env*)",
      "Bash(tail *.env*)",
      "Bash(less *.env*)",
      "Bash(more *.env*)",
      "Bash(grep *.env*)",
      "// -- Catastrophic rm patterns (literal-match defense-in-depth) --",
      "Bash(rm -rf /)",
      "Bash(rm -rf /*)",
      "Bash(rm -fr /)",
      "Bash(rm -fr /*)",
      "Bash(rm -rf ~)",
      "Bash(rm -rf ~/*)",
      "Bash(rm -rf $HOME)",
      "Bash(rm -rf $HOME/*)"
    ]
  },
  "sandbox": {
    "enabled": true
  }
}

MCP servers (1)

serversourceest. tokens
mcp.socket.dev · "socket-mcp" remote · remote 2.5k

Skills (17)

agent-routingbackend-conventionsclaude-md-maintenancecoding-principlescontext-managementcoordinator-modefrontend-design-systemgit-conventionsmemory-architectureplanning-with-filesproject-patternsprompt-engineeringreview-and-handoffsecurity-checklistsubagent-usagetestingverification

Subagents (18)

bug-fixer
model: sonnet
Diagnoses and fixes bugs
build-fixer
model: sonnet
Diagnoses and fixes build failures
build-validator
model: haiku
Validates that the project builds and all tests pass
changelog-generator
model: haiku
Generates changelog from commits
ci-fixer
model: sonnet
Diagnoses and fixes CI/CD failures
code-simplifier
model: sonnet
Reviews changed code and simplifies overly complex implementations
dependency-manager
model: haiku
Reviews dependency health and updates
deploy-validator
model: sonnet
Validates deployment readiness
doc-writer
model: sonnet
Writes and updates documentation
docker-helper
model: sonnet
Reviews Docker configs for best practices
e2e-runner
model: sonnet
Writes and runs end-to-end tests
performance-auditor
model: sonnet
Analyzes code for performance issues
plan-reviewer
model: opus
Reviews implementation plans for specificity, gaps, and executability
refactorer
model: sonnet
Refactors code to improve maintainability
security-reviewer
model: opus
Reviews code for security vulnerabilities
test-writer
model: sonnet
Writes comprehensive, meaningful tests for recently changed code
upstream-watcher
model: sonnet
Cross-references new Anthropic upstream changes against the current project's scaffolded infrastructure and produces an impact report
verify-app
model: sonnet
Verifies the running application end-to-end — tests actual behavior, not just code reading

Hooks (14)

eventmatcherruns
PostToolUseWrite|Editp=${WORCLAUDE_HOOK_PROFILE:-standard}; case "$p" in minimal) exit 0;; esac; file=$(jq -r '.tool_input.file_path // empty' 2>/dev/null); [ -n "$file" ] && [ -f "$file" ] && npx --silent prettier --write "$file" 2>/dev/null || true
PostToolUseWrite|Editp=${WORCLAUDE_HOOK_PROFILE:-standard}; case "$p" in strict) ;; *) exit 0;; esac; npx tsc --noEmit 2>/dev/null || echo '[Hook] TypeScript errors detected' >&2
PostCompact*cat CLAUDE.md && cat docs/spec/PROGRESS.md 2>/dev/null || true
PreCompact*test -f .claude/hooks/pre-compact-save.cjs && node .claude/hooks/pre-compact-save.cjs || true
SessionStart*echo '=== CLAUDE.md ==='; cat CLAUDE.md 2>/dev/null; echo; echo '=== PROGRESS ==='; cat docs/spec/PROGRESS.md 2>/dev/null; echo; echo '=== LAST SESSION ==='; f=$(ls -t .claude/sessions/*.md 2>/dev/null | head -1); if [ -n "$f" ]; then cat "
SessionEnd*p=${WORCLAUDE_HOOK_PROFILE:-standard}; case "$p" in minimal) exit 0;; esac; notify-send 'Claude Code' 'Session needs attention' 2>/dev/null || true
Stop*p=${WORCLAUDE_HOOK_PROFILE:-standard}; case "$p" in minimal) exit 0;; esac; test -f .claude/hooks/learn-capture.cjs && node .claude/hooks/learn-capture.cjs || true
UserPromptSubmit*p=${WORCLAUDE_HOOK_PROFILE:-standard}; case "$p" in minimal) exit 0;; esac; test -f .claude/hooks/correction-detect.cjs && node .claude/hooks/correction-detect.cjs || true
UserPromptSubmit*p=${WORCLAUDE_HOOK_PROFILE:-standard}; case "$p" in minimal) exit 0;; esac; test -f .claude/hooks/skill-hint.cjs && node .claude/hooks/skill-hint.cjs || true
UserPromptSubmit*p=${WORCLAUDE_HOOK_PROFILE:-standard}; case "$p" in minimal) exit 0;; esac; test -f .claude/hooks/obs-command-invocations.cjs && node .claude/hooks/obs-command-invocations.cjs || true
Notification*p=${WORCLAUDE_HOOK_PROFILE:-standard}; case "$p" in minimal) exit 0;; esac; notify-send 'Claude Code' 'Session needs attention' 2>/dev/null || true
InstructionsLoaded*p=${WORCLAUDE_HOOK_PROFILE:-standard}; case "$p" in minimal) exit 0;; esac; test -f .claude/hooks/obs-skill-loads.cjs && node .claude/hooks/obs-skill-loads.cjs || true
SubagentStart*p=${WORCLAUDE_HOOK_PROFILE:-standard}; case "$p" in minimal) exit 0;; esac; test -f .claude/hooks/obs-agent-events.cjs && node .claude/hooks/obs-agent-events.cjs || true
SubagentStop*p=${WORCLAUDE_HOOK_PROFILE:-standard}; case "$p" in minimal) exit 0;; esac; test -f .claude/hooks/obs-agent-events.cjs && node .claude/hooks/obs-agent-events.cjs || true

Slash commands (19)

/build-fix/commit-push-pr/compact-safe/conflict-resolver/end/learn/observability/refactor-clean/review-changes/review-plan/setup/start/status/sync/techdebt/test-coverage/update-claude-md/upstream-check/verify

Permissions

deny (31)
// -- Secret files (Read/Edit — Claude's own tools) --
Read(./.env)
Read(./.env.*)
Read(./secrets/**)
Edit(./.env)
Edit(./.env.*)
Edit(./secrets/**)
Read(./*.pem)
Read(./*.key)
Read(./id_rsa)
Read(./id_ed25519)
// -- SSH and cloud creds (home-relative) --
Read(~/.ssh/**)
Read(~/.aws/credentials)
Read(~/.config/gh/hosts.yml)
// -- Bash file-view commands targeting .env --
Bash(cat *.env*)
Bash(head *.env*)
Bash(tail *.env*)
Bash(less *.env*)
Bash(more *.env*)
Bash(grep *.env*)
// -- Catastrophic rm patterns (literal-match defense-in-depth) --
Bash(rm -rf /)
Bash(rm -rf /*)
Bash(rm -fr /)
Bash(rm -fr /*)
Bash(rm -rf ~)
Bash(rm -rf ~/*)
Bash(rm -rf $HOME)
Bash(rm -rf $HOME/*)
ask (0)
—
allow (104)
// -- Read-only / Exploration --
Bash(find:*)
Bash(grep:*)
Bash(cat:*)
Bash(ls:*)
Bash(head:*)
Bash(tail:*)
Bash(wc:*)
Bash(which:*)
Bash(tree:*)
Bash(diff:*)
Bash(sort:*)
Bash(uniq:*)
Bash(awk:*)
Bash(sed:*)
Bash(cut:*)
Bash(jq:*)
Bash(xargs:*)
Bash(ps:*)
Bash(du:*)
Bash(df:*)
Bash(env:*)
Bash(printenv:*)
// -- Git --
Bash(git:*)
Bash(gh:*)
// -- Common Dev Tools --
Bash(echo:*)
Bash(mkdir:*)
Bash(touch:*)
Bash(cp:*)
Bash(mv:*)
Bash(curl:*)
Bash(wget:*)
Bash(tar:*)
Bash(zip:*)
Bash(unzip:*)
Bash(rm:*)
Bash(make:*)
Bash(npm test:*)
Bash(npm run:*)
Bash(cd:*)
// -- Read Permissions --
Read(src/**)
Read(tests/**)
Read(templates/**)
Read(docs/**)
Read(.claude/**)
Read(*.md)
Read(*.json)
Read(*.js)
// -- Edit Permissions --
Edit(.claude/**)
Edit(docs/**)
Edit(src/**)
Edit(tests/**)
Edit(test/**)
Edit(README*)
Edit(*.md)
Edit(package.json)

Similar rigs

0xquinto/bcherny-claude
Boris Cherny's Claude Code configuration - commands, agents, and settings
★ 360 project Claude Code 6 agents 3 hooks 5mo ago
Orchestrator 1.1k tok ·
georgegkoumas/My-Claude-Code-Setup
My version of the https://github.com/0xquinto/bcherny-claude/tree/main
★ 1 setup Claude Code 6 agents 3 hooks 6mo ago
Orchestrator 942 tok ·
heymegabyte/agent-skills
Agent Skills — agent-neutral autonomous product-building OS for 32+ AI coding tools. 23 skill categories · 28 agents · 149 reference docs · 37 platform variants. One-line prompts → deployed products on Cloudflare Workers.
★ 22 project Claude CodeCodexCursor 1 mcp 1 skills 28 agents 4 hooks 4d ago
YOLO Cowboy 8.8k tok ·
RohiRIK/claude-code-config
Personal Claude Code global config — hooks, agents, skills, commands
★ 10 setup Claude CodeCodex 2 skills 13 agents 14 hooks 3mo ago
YOLO Cowboy 2.8k tok ·
copied ✓