Reseek
Claude Code · cheat sheet

Thirty cheats that make people say "wait, you can do that?"

The non-obvious moves. The stuff that turns Claude Code from "faster way to type" into something your whole team actually gets value from. One snippet each, a sentence on why it matters. Skim in five minutes. Steal what fits.

30 cheats 6 featured ~5 min skim Updated 2026

Slash commands

You trigger these. Just markdown files in .claude/commands/ that you check in so everyone gets them.

07

Team review on demand

/review              # current diff
/review src/auth.ts  # specific file

Bake your senior engineer's review checklist into a command. One button, same eight findings every time, including the days she's wall-to-wall in meetings.

08

Incident copilot

/incident PAGER-4421

Pulls logs, traces, recent deploys through MCP and hands back a Slack-ready post with the three most likely causes. Mostly it saves you the first 15-20 minutes of every page where you're just gathering the obvious stuff.

09

Better commit messages

/commit

Reads the staged diff, writes a commit message in your team's house style. It's better than the -m "wip" you were going to type.

10

Pass arguments verbatim

---
description: ...
argument-hint: [pr number]
---
Review PR $ARGUMENTS for ...

$ARGUMENTS in a command file gets replaced with whatever the user typed after the command. It's the simplest way to parameterize a workflow without writing a real CLI.

Context & memory

CLAUDE.md gets loaded into every session automatically. Put opinions in here, not descriptions of what the code already says.

11

Hierarchical CLAUDE.md

./CLAUDE.md          # root rules
./src/api/CLAUDE.md  # only loads in api/
./db/CLAUDE.md       # only loads in db/

Specialized rules only load when Claude's actually working in that subtree. So your frontend sessions don't get bloated with database conventions nobody's touching.

12

Personal style file

~/.claude/CLAUDE.md:
- Be terse. No emojis.
- Never recap what you just did.
- Never say "as you can see"

Your personal rules follow you into every project without ending up in the team's shared file. Good place for the "stop apologizing" stuff.

13

File mentions with @

Explain @src/auth/session.ts
Compare @old/handler.ts vs @new/handler.ts

Inline file references. No copy-paste, no "let me read that first." Claude just pulls it in.

14

Manual context reset

/clear      # reset conversation
/compact    # squeeze the context

Long sessions get heavy. /clear wipes it; /compact keeps the gist and drops the noise. Either one beats opening a new terminal and re-explaining everything.

Subagents

Isolated context, scoped tools, fire-and-forget. They live in .claude/agents/.

15

Read-only reviewer

---
name: code-reviewer
tools: Read, Grep, Bash
---

No Write, no Edit. A reviewer that can't "helpfully" go fix the thing it's supposed to be reviewing. Capability boundaries hold up better than asking nicely.

16

Spec-writer first, code second

Dispatch spec-writer:
"Build X. Return spec only."
Then implement from the spec.

Engineers (and Claude) love jumping straight into code. A spec-writer subagent in front of that instinct costs about 30 seconds. Saves you from rewriting the wrong thing tomorrow.

17

Description = trigger phrases

description: Use when the user asks
  to write tests, add test coverage, or
  fix a failing test in this codebase.

Skills auto-invoke by matching what the user said against the description field. Write vague descriptions and they basically never fire. Spell out the trigger phrases and they fire when you want them to.

18

Bootstrap Claude with Claude

"Write a slash command that takes
a Linear ticket URL and produces
a minimal reproduction case."

Use Claude to write Claude's own config. It all ends up as markdown, which (conveniently) is the thing Claude is best at producing.

Hooks & guardrails

Plain shell commands, deterministic. Configured in .claude/settings.json. Non-zero exit blocks the action.

19

Auto-format every edit

PostToolUse on Write|Edit:
  prettier --write && eslint --fix

Claude stops writing unformatted code. You stop getting prettier-only PRs. Takes about five minutes.

20

Block secrets before they're written

PreToolUse on Write|Edit:
  grep for api[_-]?key|secret|token
  → exit 1 if matched

Fifteen minutes of bash heads off most of the "uh, Claude committed our API key" stories you hear from other teams.

21

Block dangerous git

PreToolUse on Bash:
  match git push -f, reset --hard,
  rm -rf / → exit 1

The really catastrophic commands die before they run. Cheap insurance against the kind of accident you only need to have once.

22

Auto-load git context at session start

SessionStart:
  echo "branch: $(git branch --show-current)
        last:   $(git log -1 --oneline)"

Every session starts already knowing what branch you're on and what you last did. Skips the first half-minute of "okay so where were we."

CLI & headless

Claude Code outside the interactive terminal. Scripts, pipes, CI jobs.

23

Continue last session

claude -c

Picks up right where you left off. No more starting from zero because your terminal crashed.

24

Named parallel sessions

claude -r feature-auth
claude -r incident-2024-12-03

Keep multiple work streams alive without them bleeding into each other. Named, resumable, swap with a flag. Helpful when you're juggling a feature and a fire at the same time.

25

Headless in CI

claude -p --output-format json \\
  --allowed-tools "mcp__github__*,Read" \\
  "/review-pr $PR_NUMBER" > out.json

Every PR gets a pass before a human ever opens it. Scope the toolset with --allowed-tools so the CI job can't do more than it should.

26

Personal overrides without polluting team config

.claude/settings.local.json  # gitignored
.claude/settings.json        # committed

The local file overrides the team file. So you can turn off that one annoying hook for yourself without turning it off for the whole team.

MCP — connecting your stack

Model Context Protocol. A safer way to expose external tools and data to Claude.

27

Read-only Postgres

claude mcp add pg -- \\
  npx server-postgres \\
  "postgresql://readonly@..."

No more guessing column names. Claude queries the real schema. Read-only means the worst case is bounded (which is the only reason I'd hand it db credentials at all).

28

Custom MCP for your internal API

// ~50 lines of TS using @mcp/sdk
server.tool("get_customer", {#123; id }#125;, ...)
server.tool("get_billing", {#123; id }#125;, ...)

The thing the off-the-shelf servers can't do: teach Claude your business. Maybe half a day of work. Pays itself back the first time someone asks "wait, what's the rate limit for tier-2 again?"

29

Plan-then-execute

/plan
# review and edit the plan
# approve before any file is touched

Forces Claude to lay out the whole multi-file change before touching anything. You read the plan, edit it, then say go. Most of the "the AI went off the rails" stories start with someone skipping this step.

30

Iterate visually

[paste current screenshot]
[paste target screenshot]
"Make mine look like the second one"

Way faster than trying to describe UI changes in words. Pictures in, code out.

The cheats are the tip of it.

The real payoff comes from combining them. The free Reseek course walks through that, module by module, with artifacts you can actually use.

Start the free course → About Reseek