claude code patterns, battle-tested across yc startups, public tech companies, and unicorns. maintained by someone who uses claude code as their job.
new here? start with the tips index or skim hooks and automation.
three plugins, one marketplace.
lore@anipottsevery session mined into sqlite. query costs, tools, errors, hotspots, loops, and full-text search across your own history. everything local.cc@anipottscross-session awareness and messaging. plus atimesubsystem:/cc:time-estimategives realistic claude-code time grounded in your session history, not optimistic guesses.time@anipotts3-meter fuel gauge (5-hour session, 7-day weekly, 200k context). pre-turn hook nudges claude toward cleaner handoffs as the meters fill./fuel statereads them directly;/fuel handoffdrafts a stopping point.
> /cc:time-estimate "rewrite auth middleware and add tests"
CC: ~22 min active (standard mode, Opus 4.7 high)
your time: ~15 min review
/plugin marketplace add anipotts/claude-code-tips # add marketplace (one time)
/plugin install lore@anipotts # install lore (session analytics)
/plugin install cc@anipotts # install cc (cross-session messaging)
/plugin install time@anipotts # install time (fuel gauge + estimates)then: copy safety-guard.sh to block dangerous commands. read a tip. done.
hundreds of sessions across dozens of projects. $200/mo max plan.
same usage would cost ~$12K on the API with caching, ~$95K without. no autonomous loops. no cron jobs. every session starts with me typing a prompt. how the cost math works →
/plugin marketplace add anipotts/claude-code-tips # add marketplace (one time)
/plugin install lore@anipotts # install lore (session analytics)
/plugin install cc@anipotts # install cc (cross-session messaging)
/plugin install time@anipotts # install time (fuel gauge + estimates)you get lore · session mining to sqlite. costs, search, error memory, pattern detection. all data stays local at ~/.claude/lore/lore.db.
/lore today's sessions, cost, top tools
/lore search "websocket" full-text search across all conversations
/lore mistakes error patterns claude keeps repeating
/lore hotspots most-edited files across sessions
/lore loops repeated patterns across sessions
start with lore + the safety-guard hook. add more as you go. lore docs →
cross-session messaging and the time subsystem. see what other claude code sessions are doing, send messages between them, and get realistic time estimates grounded in your own session history.
/plugin install cc@anipotts/cc show active sessions
/cc send merizo "pause" message another session
/cc:time-estimate <task> ranged CC estimate, uses your current model + effort
/cc:time-calibrate diff real throughput (from lore.db) against the rule
/cc:time-benchmark guided A/B/C across effort levels on your model
hooks are the difference between "claude does what i want" and "claude does whatever it feels like." CLAUDE.md gives guidance. hooks give enforcement. one is a suggestion, the other is a wall.
this repo has 9 hooks you can drop into any project. safety-guard blocks force pushes, rm -rf /, and curl | bash. no-squash blocks squash merges. context-save preserves state before compaction. pick the ones that fit your workflow. hook guide →
multiple claude instances working simultaneously on the same codebase, each in its own git worktree. the coordinator assigns tasks, collects results, merges the best approach.
i use this for parallel research, trying risky changes safely, and comparing approaches side-by-side without touching my working tree. how i use agent teams →
this is why the $200/mo plan is the best deal in AI coding. claude code caches your system prompt, tools, and CLAUDE.md as a prefix. 91% of my input tokens hit the cache, meaning i pay 10% of the input cost on 91% of my reads.
the key: keep your CLAUDE.md short and stable. every edit breaks the prefix cache. mine is 30 lines and changes maybe once a week. the full cost breakdown →
short, standalone techniques. each one is something you can use in your next session.
| tip | what you learn |
|---|---|
| prompt caching | get 97%+ cache hit rates, slash your bill |
| safety hooks | block force pushes and rm -rf in 5 minutes |
| settings hierarchy | project vs global vs local settings |
| session length | why shorter sessions are more efficient (with data) |
| ultrathink | force extended thinking for complex problems |
| context management | compaction strategies, active tool rate, keeping sessions tight |
| plan mode | when planning saves time vs when it wastes it |
| fast mode | same model, faster output, the tradeoff |
| plugins | build a plugin from scratch, what makes one worth installing |
| subagents | agent teams, worktree isolation, when parallel pays off |
| mcp integration | wire up MCP servers, use them inside sessions |
| hooks v2 | command vs http vs prompt hooks, the async pattern |
copy one, wire it up, done. each is a standalone bash script. full guide →
| hook | event | what it does |
|---|---|---|
| safety-guard | PreToolUse | blocks force push, rm -rf /, DROP TABLE, curl-pipe-sh |
| no-squash | PreToolUse | blocks squash merges |
| panopticon | PostToolUse | logs every tool call to sqlite |
| context-save | PreCompact | saves context before compression |
| notify | Notification | routes to macOS, Slack, ntfy |
4 more hooks
| hook | event | what it does |
|---|---|---|
| commit-nudge | PostToolUse | reminds you to commit after N edits |
| version-stamp | SessionEnd | auto-updates "tested with" stamps |
| stale-branch | SessionStart | warns about gone tracking branches |
| md-lint-fix | PostToolUse | auto-fixes markdown lint on save |
copy to .claude/agents/ and invoke with /agent <name>. each teaches a different pattern. guide →
| agent | pattern | what it does |
|---|---|---|
| watch-tests | daemon | watches files, runs tests, proposes fixes |
| try-worktree | worktree | tries risky changes in isolated worktrees |
| arch-review | quick review | fast architecture smell-test |
| write-pr | git integration | PR descriptions from your diff |
| command | what it does |
|---|---|
/lore | usage data · costs, sessions, search, patterns |
/ship | stage, commit, push, open PR in one command |
/improve | propose CLAUDE.md updates from git history |
plus 2 example commands you can copy: /sweep, /quicktest.
| what | |
|---|---|
| cost reality | what claude code actually costs, the prompt caching math |
| mistakes i made | what burned me so you can skip it |
| automation | patterns for safe daemons, cron, and github actions with claude code |
| session workflow | how i work day-to-day with claude code |
| worktrees | parallel exploration with the desktop app |
diplomatic, data-driven, no FUD. every claim cites a source.
vs cursor · vs codex · vs gemini · vs antigravity · pricing
- CLAUDE.md templates · starter configs for TypeScript, Python, Rust, Next.js
- example agents · 4 agents, each teaching a different pattern
- example commands · 2 commands you can copy to any project
- handoff plugin · PreCompact context preservation
- broadcast plugin · async notifications on git events
this repo runs on its own patterns.
- CI workflows for validation, freshness, competitive intel, community signal, releases, AI-assisted review
- 9 standalone hooks + per-plugin hooks across cc / lore / time
- AI-powered checks use haiku so monthly CI cost stays under a couple of dollars
- automation handles the mechanical work so judgment-heavy decisions stay human
these all came out of living in claude code every day. each solves a specific problem i kept hitting.
- lore · session mining to sqlite. costs, search, error memory, pattern detection
- claudemon · real-time session monitoring across projects and machines
- cc · multi-session awareness. see what other sessions are doing, send messages between them
- imessage-mcp · MCP server for read-only iMessage history. 26 tools, zero network requests
- anipotts.com/thoughts · long-form
- buttondown.com/anipotts · newsletter
- @anipottsbuilds · short-form
MIT · built by anipotts