Mike Swanson
d4d24b5afd
The context-lookup standard + CODING_GUIDELINES still said 'GrepAI First' unconditionally.
Updated both to: wiki first for known-entity facts; GrepAI/Grep-before-read for code+discovery.
Keeps the search-before-read token discipline; removes the wiki overlap. Completes the
positioning fix started in e8a689b0 (all 4 sources now consistent: CORE, EXTENDED, standard,
guidelines).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
63 lines
2.8 KiB
Markdown
63 lines
2.8 KiB
Markdown
---
|
|
name: grepai-first
|
|
description: Wiki first for known-entity facts; then search with GrepAI/Grep before opening any file for code/discovery; Read only when full content is needed
|
|
applies-to: all
|
|
---
|
|
|
|
# Context Lookup — search before reading (wiki first for known entities)
|
|
|
|
Two-part rule:
|
|
|
|
1. **Known-entity facts** (a specific client/project/system — its IPs, creds paths, architecture):
|
|
check the **wiki** (`wiki/`) FIRST. It is the synthesized truth layer and is already distilled —
|
|
cheaper than re-deriving from raw logs/code.
|
|
2. **Everything else** (code, discovery, un-compiled detail): search with **GrepAI or Grep before
|
|
opening any file**. Only open a file when you need its full content for editing or line-by-line
|
|
review.
|
|
|
|
GrepAI's irreplaceable value is **code** (call-graph tracing over the Rust+TS corpus the wiki can't
|
|
see). Do NOT GrepAI something the wiki already answers — that's redundant overlap.
|
|
|
|
## Lookup table
|
|
|
|
| Goal | Tool |
|
|
|------|------|
|
|
| Find where a function is defined | `grepai_search` or `Grep` |
|
|
| Understand how a feature works | `grepai_search` |
|
|
| Find all callers of a function | `grepai_trace_callers` |
|
|
| Find what a function calls | `grepai_trace_callees` |
|
|
| Full file content needed (edit, review) | `Read` |
|
|
| Recent changes to a file | `git log`, then `Read` specific file |
|
|
| "What did we do with client/system X?" | **wiki article first**, then `grepai_search` over session logs for detail below the wiki's summary |
|
|
| "How is Y configured?" (known entity) | **wiki first**, then `grepai_search` / the specific file |
|
|
| "How is Y configured?" (code/unknown) | `grepai_search` before opening any file |
|
|
|
|
## Token cost rationale
|
|
|
|
Reading a 500-line file to find one function costs approximately 3,000 tokens. A targeted GrepAI or Grep search costs approximately 100 tokens and returns only the relevant lines. At scale, reading files for context without searching first wastes context window and increases latency.
|
|
|
|
Never open a large file to scan for context. Search first; read only if the search result is insufficient or if you need to edit the file.
|
|
|
|
## GrepAI specifics
|
|
|
|
- CLI: `D:/claudetools/grepai.exe search "query" --json -c -n 5`
|
|
- MCP tools: `grepai_search` (primary), `grepai_trace_callers`, `grepai_trace_callees`
|
|
- The GrepAI index covers session logs, skill files, and project docs with boosted relevance for `.claude/` content
|
|
- The watcher (scheduled task "GrepAI Watcher - claudetools") keeps the index current automatically
|
|
|
|
## Common search queries
|
|
|
|
```bash
|
|
# Find where a setting is configured
|
|
grepai_search "vault_path"
|
|
|
|
# Understand how the Syncro skill handles billing
|
|
grepai_search "timer_entry charge_timer"
|
|
|
|
# Find what we did with a specific client or feature
|
|
grepai_search "Cascades DMARC"
|
|
|
|
# Locate a function definition
|
|
Grep --pattern "fn collect_temps" --type rust
|
|
```
|