skills/intel/SKILL.md
Query, inspect, or refresh codebase intelligence files in .planning/intel/
npx skillsauth add jnuyens/gsd-plugin gsd:intelInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
STOP -- DO NOT READ THIS FILE. You are already reading it. This prompt was injected into your context by Claude Code's command system. Using the Read tool on this file wastes tokens. Begin executing Step 0 immediately.
Before ANY tool calls, display this banner:
GSD > INTEL
Then proceed to Step 1.
Check if intel is enabled by reading .planning/config.json directly using the Read tool.
DO NOT use the gsd-tools config get-value command -- it hard-exits on missing keys.
.planning/config.json using the Read toolconfig.intel && config.intel.enabled === trueintel.enabled is NOT explicitly true: display the disabled message below and STOPintel.enabled is true: proceed to Step 2Disabled message:
GSD > INTEL
Intel system is disabled. To activate:
gsd-sdk query config-set intel.enabled true
Then run /gsd:intel refresh to build the initial index.
Parse $ARGUMENTS to determine the operation mode:
| Argument | Action |
|----------|--------|
| query <term> | Run inline query (Step 2a) |
| status | Run inline status check (Step 2b) |
| diff | Run inline diff check (Step 2c) |
| refresh | Spawn intel-updater agent (Step 3) |
| No argument or unknown | Show usage message |
Usage message (shown when no argument or unrecognized argument):
GSD > INTEL
Usage: /gsd:intel <mode>
Modes:
query <term> Search intel files for a term
status Show intel file freshness and staleness
diff Show changes since last snapshot
refresh Rebuild all intel files from codebase analysis
Run:
gsd-sdk query intel.query <term>
Parse the JSON output and display results:
"disabled": true, display the disabled message from Step 1 and STOPNo intel matches for '<term>'. Try /gsd:intel refresh to build the index.STOP after displaying results. Do not spawn an agent.
Run:
gsd-sdk query intel.status
Parse the JSON output and display each intel file with:
updated_at timestampSTOP after displaying status. Do not spawn an agent.
Run:
gsd-sdk query intel.diff
Parse the JSON output and display:
If no snapshot exists, suggest running refresh first.
STOP after displaying diff. Do not spawn an agent.
Display before spawning:
GSD > Spawning intel-updater agent to analyze codebase...
Spawn a Task:
Task(
description="Refresh codebase intelligence files",
prompt="You are the gsd-intel-updater agent. Your job is to analyze this codebase and write/update intelligence files in .planning/intel/.
Project root: ${CWD}
Prefer: gsd-sdk query <subcommand> (installed gsd-sdk on PATH). Legacy: node $HOME/.claude/get-shit-done/bin/gsd-tools.cjs
Instructions:
1. Analyze the codebase structure, dependencies, APIs, and architecture
2. Write JSON intel files to .planning/intel/ (stack.json, api-map.json, dependency-graph.json, file-roles.json, arch-decisions.json)
3. Each file must have a _meta object with updated_at timestamp
4. Use `gsd-sdk query intel.extract-exports <file>` to analyze source files
5. Use `gsd-sdk query intel.patch-meta <file>` to update timestamps after writing
6. Use `gsd-sdk query intel.validate` to check your output
When complete, output: ## INTEL UPDATE COMPLETE
If something fails, output: ## INTEL UPDATE FAILED with details."
)
Wait for the agent to complete.
After the agent completes, run:
gsd-sdk query intel.status
Display a summary showing:
testing
Capture or review how this project connects to external systems (GitHub, AWS, npm, SSH, etc.) so future sessions know the auth recipe. Auto-detection hook logs candidate captures to an inbox; this skill promotes them to permanent recipes in `.planning/AUTH-RECIPES.md` and optionally to user-global memory at `~/.claude/auth-recipes/`.
tools
Initialize a new project using Documentation-Driven Development. Research, then write user-facing docs (SPEC.md) as the spec, then user validates docs, then phases derive from doc sections. Best for CLIs, libraries, SDKs, APIs, plugin systems, anything with a well-defined user-facing surface.
tools
Plan an MVP-mode phase — captures an "As a / I want to / So that" user story, runs SPIDR splitting, then delegates to plan-phase
testing
Extract decisions, lessons, patterns, and surprises from completed phase artifacts