Fighter90/career-ops-ui
Clean, docs-style web UI for the career-ops AI job-search pipeline. Search ATS adapters (Greenhouse/Ashby/Lever) + regional portals (hh.ru/Habr Career), evaluate JDs, track applications — all from the browser.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit Fighter90/career-ops-ui/.claude ./rig-career-ops-ui # 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.
$ npx degit Fighter90/career-ops-ui/.agents/skills/swarm .claude/skills/swarm $ npx degit Fighter90/career-ops-ui/.claude/skills/contributor-pr .claude/skills/contributor-pr $ npx degit Fighter90/career-ops-ui/.claude/skills/hermes-bridge .claude/skills/hermes-bridge $ npx degit Fighter90/career-ops-ui/.claude/skills/parent-sync .claude/skills/parent-sync
$ curl -fsSL --create-dirs -o .claude/agents/spa-view-reviewer.md https://raw.githubusercontent.com/Fighter90/career-ops-ui/main/.claude/agents/spa-view-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/test-isolation-reviewer.md https://raw.githubusercontent.com/Fighter90/career-ops-ui/main/.claude/agents/test-isolation-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/web-ui-route-reviewer.md https://raw.githubusercontent.com/Fighter90/career-ops-ui/main/.claude/agents/web-ui-route-reviewer.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (4)
Subagents (3)
| spa-view-reviewer model: sonnet | Use this agent after editing any file under `public/js/views/*.js`, `public/js/router.js`, or `public/js/lib/*.js`. It checks for CSP-safe DOM patterns, i18n coverage, accessibility basics, and route |
| test-isolation-reviewer model: sonnet | Use this agent after adding or modifying any file in `tests/` to verify the test will pass in CI (no parent-project dependency, no live network, no port collision). Invoke proactively after every test |
| web-ui-route-reviewer model: sonnet | Use this agent for any change that adds, edits, or removes an Express route in `server/index.mjs` or `server/lib/*.mjs`, or any client-side fetch in `public/js/api.js`. It enforces the project's secur |
Slash commands (3)
/codebase-tour/sdd-status/swarm
Similar rigs
Ovich/swarmstorm
Multi-agent orchestration for Claude Code, Codex and Cursor: parallel coding agents that settle shared files before the merge, QA agents that test the running app, clickable prototypes, workbenches and live plans in aiview. Your own subscri
Minimalist 2.3k tok · · Q0
ben-alkov/the_swarm
Claude Code plugin for multi-pattern multi-agent orchestration, using CC's built in Agent Swarm as the engine — dispatches and coordinates specialist sub-agents in fan-out, pipeline, map-reduce, speculative, and swarm configurations.
Pragmatist 671 tok · · Q0
HimanshuJ16/tradefloor
A multi-agent trading desk for Claude Code, Codex and Antigravity. Quotes calibrated odds instead of opinions, scans markets before the open and during the session, and grades every call it makes. 41 exchanges including NSE, no API keys. No
Pragmatist 4.7k tok · · Q0
Nowely/agent-skills
Run Codex as a Claude Code subagent with rights declared per call — read-only analysis, or writing and running tests inside a git worktree — and an exit code that reflects what actually ran.
Skill Collector 119 tok · · Q0