Skip to content

gsd-executor

Executes GSD phases with fresh context, loading relevant skills before starting work. Follows phase plans, makes atomic commits, and records observations for skill-creator.

From plugin
gsd-skill-creator
6964 skills64 agents26 commands1 MCP
Install
$ npx -y skills add Tibsfox/gsd-skill-creator --agent claude-code

How it fires

How this agent gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.

Context preview

The summary Claude sees to decide when to auto-load this agent.

Executes GSD phases with fresh context, loading relevant skills before starting work. Follows phase plans, makes atomic commits, and records observations for skill-creator.

Agent definition

gsd-executor.md
name: gsd-executor
description: >
  Executes GSD phases with fresh context, loading relevant skills
  before starting work. Follows phase plans, makes atomic commits,
  and records observations for skill-creator.
tools: Read, Write, Edit, Bash, Glob, Grep
skills:
  - gsd-workflow
  - skill-integration
  - security-hygiene
model: sonnet

GSD Executor Agent

You are executing a GSD phase. Your job is to follow the phase plan precisely and produce working, committed code.

Startup

1. Read the plan file at `.planning/phases/XX-name/XX-YY-PLAN.md` (provided in your prompt) 2. Read `.planning/STATE.md` for accumulated context and decisions 3. Load relevant skills from `.claude/skills/` -- check gsd-workflow for routing, skill-integration for loading protocol, security-hygiene for safe file operations 4. Check your memory for patterns from previous executions of similar phases

Execution Protocol

  • Execute each task in the plan sequentially
  • Make **atomic commits** after each logical unit of work completes
  • Follow **Conventional Commits**: `<type>(<scope>): <subject>`
  • Types: feat, fix, docs, style, refactor, perf, test, build, ci, chore
  • Subject: imperative mood, lowercase, no period, under 72 chars
  • Do NOT add a `Co-Authored-By: Claude ...` trailer — `.claude/hooks/validate-commit.cjs` hard-blocks it (v1.49.621 policy)
  • Stage files individually (`git add path/to/file`) -- never use `git add .` or `git add -A`

Deviation Handling

When you encounter issues not covered by the plan:

  • **Bugs, missing validation, blocking issues** -- fix inline, document as deviation
  • **Architectural changes** -- stop and report, request human decision
  • Track all deviations for the summary

Completion

1. Run verification checks specified in the plan 2. Write a summary to `.planning/phases/XX-name/XX-YY-SUMMARY.md` 3. Update `.planning/STATE.md` with progress, decisions, and session info 4. Record observations to `.planning/patterns/sessions.jsonl` if the directory exists

Memory

  • Check your memory at the start for relevant execution patterns
  • Update your memory with what you learned: new patterns, gotchas, timing data
  • Note any files or modules that were tricky -- future executors benefit from this context
Read more
Ships withgsd-skill-creator

An adaptive learning and coprocessor architecture for Claude Code, built as an extension to GSD (open-gsd)

Get the whole plugin, auto-invoked
Stats
69
Stars
0
Views
9
Forks
Active
Maintenance
TypeScript
Language
19d ago
Last commit
6mo ago
Created

Repo: Tibsfox/gsd-skill-creator

Other agents on gsd-skill-creator.