agentleFS
sp1esp1e/claude-skills/gsd-graphify/SKILL.md

gsd-graphify

Skill1 starsChanged 31 days agoMITView on GitHub

Build, query, and inspect the project knowledge graph in .planning/graphs/

4 other projects use a version of this, 4 of them edited.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

32 rules. 8 are common, 3 are distinctive, and 21 are very specific to this project.

  • 8

    Common

    Most of the 4 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 21

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Check if graphify is enabled by reading .planning/config.json directly using the Read tool.

    line 28
  2. Very specific:

    Read .planning/config.json using the Read tool

    line 32
  3. Common:

    If the file does not exist: display the disabled message below and STOP

    line 33
  4. Very specific:

    If graphify.enabled is NOT explicitly true: display the disabled message below and STOP

    line 35
  5. Very specific:

    If graphify.enabled is true: proceed to Step 2

    line 36
  6. Very specific:

    If the output contains "disabled": true, display the disabled message from Step 1 and STOP

    line 87
  7. Very specific:

    If the output contains "error" field, display the error message and STOP

    line 88
  8. Very specific:

    If no nodes found, display: No graph matches for '<term>'.

    line 89
  9. Common:

    STOP: after displaying results. Do not spawn an agent.

    line 92
  10. Very specific:

    If exists: false, display the message field

    line 103
  11. Very specific:

    If built_at_commit is non-null, also display a Source commit: line:

    line 105
  12. Very specific:

    If built_at_commit is null (pre-graphify-v0.7 graph), omit the source-commit line entirely — do not render "Source commit: unknown"

    line 109
  13. Common:

    STOP: after displaying status. Do not spawn an agent.

    line 116
  14. Very specific:

    If no snapshot exists, suggest running build twice (first to create, second to generate a diff baseline).

    line 130
  15. Common:

    STOP: after displaying diff. Do not spawn an agent.

    line 132
  16. Common:

    Run the pre-flight check first:

    line 138
  17. Very specific:

    If disabled: true: display the disabled message from Step 1 and STOP

    line 145
  18. Very specific:

    If error: display the error message and STOP

    line 146
  19. Very specific:

    If action: "spawn_agent": pre-flight passed -- proceed with the inline build below

    line 147
  20. Common:

    Run the build, copy artifacts, write the diff snapshot, and report the summary in a single foreground Bash call so the whole pipeline …

    line 157
  21. Very specific:

    Do NOT pass run_in_background: true.

    line 168
  22. Common:

    If the chain fails (non-zero exit):

    line 170
  23. Very specific:

    Do NOT delete .planning/graphs/ -- the prior valid graph remains available

    line 172
  24. Common:

    If the chain succeeds:

    line 175
  25. Very specific:

    MVP-mode rendering: When a phase has Mode: mvp in ROADMAP.md (resolved via gsd-sdk query roadmap.get-phase --pick mode), render its graph …

    line 183
  26. Very specific:

    Distinct fill color: Use #22c55e (green) for MVP-mode phase nodes.

    line 185
  27. Distinctive:

    When the phase mode is null/absent, render with the standard color and label — no behavioral change for non-MVP phases.

    line 190
  28. Distinctive:

    DO NOT spawn an agent for any operation -- build, query, status, and diff all run inline.

    line 196
  29. Very specific:

    DO NOT pass run_in_background: true for the build chain -- the operation is fast and must complete in the foreground.

    line 197
  30. Very specific:

    DO NOT modify graph files directly -- always go through graphify update .

    line 198
  31. Distinctive:

    DO NOT skip the config gate check.

    line 199
  32. Very specific:

    DO NOT use gsd-tools config get-value for the config gate -- it exits on missing keys.

    line 200

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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.

CJS-only (graphify): graphify subcommands are not registered on gsd-sdk query. Use node $HOME/.claude/get-shit-done/bin/gsd-tools.cjs graphify … as documented in this command and in docs/CLI-TOOLS.md. Other tooling may still use gsd-sdk query where a handler exists.

Step 0 -- Banner

Before ANY tool calls, display this banner:

GSD > GRAPHIFY

Then proceed to Step 1.

Step 1 -- Config Gate

Check if graphify 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.

  1. Read .planning/config.json using the Read tool
  2. If the file does not exist: display the disabled message below and STOP
  3. Parse the JSON content. Check if config.graphify && config.graphify.enabled === true
  4. If graphify.enabled is NOT explicitly true: display the disabled message below and STOP
  5. If graphify.enabled is true: proceed to Step 2

Disabled message:

GSD > GRAPHIFY

Knowledge graph is disabled. To activate:

  node $HOME/.claude/get-shit-done/bin/gsd-tools.cjs config-set graphify.enabled true

Then run /gsd-graphify build to create the initial graph.

Step 2 -- Parse Argument

Parse $ARGUMENTS to determine the operation mode:

ArgumentAction
buildRun inline build (Step 3)
query <term>Run inline query (Step 2a)
statusRun inline status check (Step 2b)
diffRun inline diff check (Step 2c)
No argument or unknownShow usage message

Usage message (shown when no argument or unrecognized argument):

GSD > GRAPHIFY

Usage: /gsd-graphify <mode>

Modes:
  build           Build or rebuild the knowledge graph
  query <term>    Search the graph for a term
  status          Show graph freshness and statistics
  diff            Show changes since last build

Step 2a -- Query

Run:

node $HOME/.claude/get-shit-done/bin/gsd-tools.cjs graphify query <term>

Parse the JSON output and display results:

  • If the output contains "disabled": true, display the disabled message from Step 1 and STOP
  • If the output contains "error" field, display the error message and STOP
  • If no nodes found, display: No graph matches for '<term>'. Try /gsd-graphify build to create or rebuild the graph.
  • Otherwise, display matched nodes grouped by type, with edge relationships and confidence tiers (EXTRACTED/INFERRED/AMBIGUOUS)

STOP after displaying results. Do not spawn an agent.

Step 2b -- Status

Run:

node $HOME/.claude/get-shit-done/bin/gsd-tools.cjs graphify status

Parse the JSON output and display:

  • If exists: false, display the message field
  • Otherwise show last build time, node/edge/hyperedge counts, and STALE or FRESH indicator
  • If built_at_commit is non-null, also display a Source commit: line:
    • commit_stale === false (rebuilt at HEAD): Source commit: <built_at_commit> (current)
    • commit_stale === true (graph behind HEAD): Source commit: <built_at_commit> (<commits_behind> commits behind HEAD)
    • commit_stale === null (unreachable commit / no git): Source commit: <built_at_commit> (freshness unknown)
  • If built_at_commit is null (pre-graphify-v0.7 graph), omit the source-commit line entirely — do not render "Source commit: unknown"

The mtime-based STALE/FRESH flag and the commit-based commit_stale measure different things and can disagree (e.g., a CI-built graph rebuilt minutes ago against an old checkout reads as FRESH on mtime but commit_stale: true). Surface both so the agent can choose.

STOP after displaying status. Do not spawn an agent.

Step 2c -- Diff

Run:

node $HOME/.claude/get-shit-done/bin/gsd-tools.cjs graphify diff

Parse the JSON output and display:

  • If no_baseline: true, display the message field
  • Otherwise show node and edge change counts (added/removed/changed)

If no snapshot exists, suggest running build twice (first to create, second to generate a diff baseline).

STOP after displaying diff. Do not spawn an agent.


Step 3 -- Build (Inline)

Run the pre-flight check first:

node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" graphify build

Parse the JSON output:

  • If disabled: true: display the disabled message from Step 1 and STOP
  • If error: display the error message and STOP
  • If action: "spawn_agent": pre-flight passed -- proceed with the inline build below

(The spawn_agent action name is historical. The skill now performs the build inline because graphify v0.7+ split the build into a fast AST-extraction phase and a separate clustering + report-write phase. Sub-agent isolation kept the cached extraction phase alive but SIGTERM'd the post-extraction phase when the agent exited, leaving the cache populated but no graph.json artifacts written. The CLI still emits the spawn_agent signal so external callers and tests keep working.)

Display:

GSD > Building knowledge graph...

Run the build, copy artifacts, write the diff snapshot, and report the summary in a single foreground Bash call so the whole pipeline survives to completion. Use a timeout of 600000 ms (10 minutes), which covers the graphify.build_timeout ceiling (default 300 s) with margin:

graphify update . \
  && cp graphify-out/graph.json .planning/graphs/graph.json \
  && cp graphify-out/graph.html .planning/graphs/graph.html \
  && cp graphify-out/GRAPH_REPORT.md .planning/graphs/GRAPH_REPORT.md \
  && node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" graphify build snapshot \
  && node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" graphify status

Do NOT pass run_in_background: true. Typical builds complete in 15-60 seconds and the entire chain must run foreground.

If the chain fails (non-zero exit):

  • Display: ## GRAPHIFY BUILD FAILED followed by the captured stderr
  • Do NOT delete .planning/graphs/ -- the prior valid graph remains available
  • STOP

If the chain succeeds:

  • Parse the trailing graphify status JSON
  • Display: ## GRAPHIFY BUILD COMPLETE with the node, edge, and hyperedge counts

MVP-Mode Node Rendering

MVP-mode rendering. When a phase has **Mode:** mvp in ROADMAP.md (resolved via gsd-sdk query roadmap.get-phase --pick mode), render its graph node with two distinct visual signals:

  1. Distinct fill color. Use #22c55e (green) for MVP-mode phase nodes. Standard phases keep the default fill color. Two-channel signaling (color + label) handles color-blind and grayscale renders.
  2. MVP label suffix. Append (MVP) to the node's label text. Example: a phase originally labeled Phase 1: User Auth renders as Phase 1: User Auth (MVP).

Both signals fire together — never just one. Per PRD Q5 decision, the goal is unambiguous visual distinction in any render context.

When the phase mode is null/absent, render with the standard color and label — no behavioral change for non-MVP phases.


Anti-Patterns

  1. DO NOT spawn an agent for any operation -- build, query, status, and diff all run inline. Sub-agent isolation terminates background bash when the agent exits, which previously truncated graphify builds mid-write and left only the cache populated (#3166).
  2. DO NOT pass run_in_background: true for the build chain -- the operation is fast and must complete in the foreground.
  3. DO NOT modify graph files directly -- always go through graphify update . and the snapshot CLI.
  4. DO NOT skip the config gate check.
  5. DO NOT use gsd-tools config get-value for the config gate -- it exits on missing keys.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.