Chalk Labs
Need help deploying cheez-search?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/paulnsorensen-cheez-search
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/cheez-search
Tools it pre-approves 3
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
mcp__tilth__tilth_search,mcp__tilth__tilth_deps,bash
What's inside
- Skill name
cheez-search- Description
- AST-aware code search using tilth MCP. Finds definitions first, then usages. Use tree-sitter structural matching instead of blind text grep. Understand dependencies and call graphs. Use when: finding where symbols are defined, tracing call chains, understanding code structure, finding all callers of a function. Do NOT use for reading files — use cheez-read. Do NOT use for editing — use cheez-write. Examples: "find where handleAuth is defined", "what calls validateToken?", "trace the ServeHTTP, HandlersChain, Next functions", "find all implementations of the UserService interface".
- License
- MIT
- Compatibility
- Requires tilth MCP server
- Allowed tools
- mcp__tilth__tilth_search,, mcp__tilth__tilth_deps,, bash
- Instructions
- 433 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# cheez-search
> **Hard dependency**: If `mcp__tilth__tilth_search` is unavailable, stop immediately and report
> "tilth MCP server is not loaded — cannot proceed." Do NOT fall back to `Grep`, `Glob`,
> or any host tool.
AST-aware code search via **tilth MCP** (`tilth_search`, `tilth_deps`).
Tree-sitter finds where symbols are **defined** — not just where strings appear.
Understand dependencies instead of blindly grepping.
---
## Core Principle: Definitions First
Traditional grep finds text matches. tilth_search finds **semantic matches**:
- Definitions: where a symbol is declared
- Usages: where it's called or referenced
- Implementations: where interfaces are implemented
Each match includes its surrounding file structure, so you know what you're
looking at without a second read.
**Why this matters:**
- "handleAuth" appears 47 times, but it's DEFINED in one place
- tilth shows the definition first, then usages ranked by relevance
- You understand the code faster with fewer tool calls
---
## Choose your search kind
All six rows below are first-class — picking the right one is the difference
between one call and a long grep walk.
| Goal | Tool | Example |
|------|------|---------|
| Find where a symbol is defined / used | `tilth_search` (default `kind: "symbol"`) | `tilth_search(query: "handleAuth", scope: "src/")` |
| Find every call site of a function | `tilth_search(kind: "callers")` | `tilth_search(query: "validateToken", kind: "callers")` |
| Find literal strings, TODOs, error messages | `tilth_search(kind: "content")` | `tilth_search(query: "TODO: fix", kind: "content")` |
| Find lines matching a regex | `tilth_search(kind: "regex")` | `tilth_search(query: "rate.?limit", kind: "regex")` |
| Match an AST shape (template with metavars) | `sg` (ast-grep, via Bash) | `sg --lang typescript -p 'JSON.parse(JSON.stringify($X))' --json src/` |
| Module import / blast-radius graph | `tilth_deps` | `tilth_deps(path: "src/auth.ts")` |
**Rule of thumb:** stay in tilth for anything name-shaped or text-shaped.
Drop to `sg` only when the pattern needs structural metavariables (`$X`,
`$$$BODY`) that tilth can't express.
---
## MCP Tool Reference
### tilth_search — Symbol and Content Search
**Basic symbol search:**
```
tilth_search(query: "handleAuth", scope: "src/")
```
**Output:**
```
# Search: "handleAuth" in src/ — 6 matches (2 definitions, 4 usages)
## src/auth.ts:44-89 [definition]
[24-42] fn validateToken(token: string)
→ [44-89] export fn handleAuth(req, res, next)
[91-120] fn refreshSession(req, res)
44 │ export function handleAuth(req, res, next) {
45 │ const token = req.headers.authorization?.split(' ')[1];
...
88 │ next();
89 │ }
── calls ──
validateToken src/auth.ts:24-42 fn validateToken(token: string): Claims | null
refreshSession src/auth.ts:91-120 fn refreshSession(req, res)
## src/routes/api.ts:34 [usage]
→ [34] router.use('/api/protected/*', handleAuth);
```
**Key features:**
- `[definition]` vs `[usage]` — know what you're looking at
- Context lines show surrounding structure (what else is in this file)
- `── calls ──` footer shows what the function calls (one-hop callees)
- Expanded source blocks include full implementation
---
## Multi-Symbol Search
Trace across files in one call:
```
tilth_search(query: "ServeHTTP, HandlersChain, Next", scope: ".")
```
Each symbol gets its own result block. The expand budget is shared — at least
one expansion per symbol, deduplicated across files.
**Use cases:**
- Understanding a flow that spans multiple types
- Tracing request handling through middleware chains
- Investigating related symbols together
---
## Callers Query — Find All Call Sites
Find all places that call a specific function using structural tree-sitter
matching (not text search):
```
tilth_search(query: "isTrustedProxy", kind: "callers", scope: ".")
```
**Output:**
```
# Callers of "isTrustedProxy" — 5 call sitesFrom paulnsorensen/cheese-flow, MIT.
More from paulnsorensen/cheese-flow
- 0.498score
nih-audit
paulnsorensen
Scan a codebase for custom code that duplicates what open-source libraries already do, then recommend which libraries to adopt.
SkillCFreshness: C★ 1Claude Code +9 - 0.495score
cure
paulnsorensen
Finish what /age started.
SkillCFreshness: C★ 1Claude Code +9 - 0.495score
age
paulnsorensen
Staff Engineer code review orchestrator.
SkillCFreshness: C★ 1Claude Code +9 - 0.495score
cleanup
paulnsorensen
Mechanical apply of /age's hash-anchored sidecar fixes via tilth_edit.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
mold
paulnsorensen
Iterative thinking amplifier for fuzzy ideas.
SkillCFreshness: C★ 1Claude Code +9 - 0.490score
milknado-execute
paulnsorensen
Use the Milknado MCP tools to pick and execute the next ready node from the Mikado graph, apply file changes, and run quality gates.
SkillCFreshness: C★ 1Claude Code +9 - 0.490score
research
paulnsorensen
Multi-source research orchestrator that routes questions across Context7 library docs, Tavily web research, codebase analysis, and GitHub examples, then…
SkillCFreshness: C★ 1Claude Code +9 - 0.437score
merge-resolve
paulnsorensen
Resolve merge conflicts, rebase conflicts, and cherry-pick failures using mergiraf (AST-aware structural merge), git rerere, and kdiff3.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
gh
paulnsorensen
Complete GitHub tasks using the gh CLI.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
cheez-read
paulnsorensen
Smart code reading using tilth MCP.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
cheez-write
paulnsorensen
Hash-anchored file editing using tilth MCP.
SkillDFreshness: D★ 1Claude Code +9 - 0.425score
milknado-plan
paulnsorensen
Use the Milknado MCP tools to decompose a goal into a Mikado-style change graph and produce a token-budgeted batch plan.
SkillDFreshness: D★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 1
- Open issues
- 25
- Last commit (this folder)
- May 1, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/paulnsorensen/cheese-flow
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from paulnsorensen
- 0.603score
bin-doctor
paulnsorensen
Audit and repair installed binaries so each tool has one install path, a clean cache, and a current pin, across mise, Homebrew, cargo, uv, npm, pnpm, bun…
SkillAFreshness: A★ 2Claude Code +9 - 0.603score
build-optimize
paulnsorensen
Optimize local build, test, and check commands with measured wall-time evidence.
SkillAFreshness: A★ 2Claude Code +9 - 0.603score
chezmoi
paulnsorensen
Guides dotfile management with chezmoi when the user says "set up dotfiles", "manage my dotfiles", "bootstrap a new machine", "chezmoi", "encrypt my SSH key…
SkillAFreshness: A★ 2Claude Code +9 - 0.600score
ci-optimize
paulnsorensen
Optimize GitHub Actions workflow wait time with measured evidence.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
cheese-board-loop
paulnsorensen
Runs the cheese-board workflow and asks the user each question it raises.
SkillAFreshness: A★ 2Claude Code +9 - 0.592score
skillz
paulnsorensen
Add, improve, audit, wedge, or autoimprove a skill.
SkillAFreshness: A★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get cheez-search running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
cheez-search skill. Agent Mart. https://agentmart.dev/skills/paulnsorensen-cheez-search (last updated 2026-10-24)