home/common/ai/resources/codex/gsd/skills/gsd-debug/SKILL.md
Systematic debugging with persistent state across context resets
npx skillsauth add kamushadenes/nix gsd-debugInstall 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.
<codex_skill_adapter>
$gsd-debug.$gsd-debug as {{GSD_ARGS}}.{{GSD_ARGS}} as empty.GSD workflows use AskUserQuestion (Claude Code syntax). Translate to Codex request_user_input:
Parameter mapping:
header → headerquestion → question"Label" — description → {label: "Label", description: "description"}id from header: lowercase, replace spaces with underscoresBatched calls:
AskUserQuestion([q1, q2]) → single request_user_input with multiple entries in questions[]Multi-select workaround:
multiSelect. Use sequential single-selects, or present a numbered freeform list asking the user to enter comma-separated numbers.Execute mode fallback:
request_user_input is rejected or unavailable, you MUST stop and present the questions as a plain-text numbered list, then wait for the user's reply. Do NOT pick a default and continue (#3018).--auto or --all),
(b) the user has explicitly approved a specific default for this question, or
(c) the workflow's documented contract says defaults are safe (e.g. autonomous lifecycle paths).GSD workflows use Task(...) (Claude Code syntax). Translate to Codex collaboration tools:
Direct mapping:
Task(subagent_type="X", prompt="Y") → spawn_agent(agent_type="X", message="Y")Task(model="...") → omit. spawn_agent has no inline model parameter;
GSD embeds the resolved per-agent model directly into each agent's .toml
at install time so model_overrides from .planning/config.json and
~/.gsd/defaults.json are honored automatically by Codex's agent router.fork_context: false by default — GSD agents load their own context via <files_to_read> blocksTask(isolation="worktree") / Agent(isolation="worktree") → no direct Codex mapping.
Codex spawn_agent does not create or bind a git worktree automatically.
Workflows that require this isolation must fail closed or use an explicit
manual worktree protocol before spawning (#3360).Spawn restriction:
spawn_agent to cases where the user has explicitly
requested sub-agents. When automatic spawning is not permitted, do the
work inline in the current agent rather than attempting to force a spawn.Parallel fan-out:
wait(ids) for all to completeResult parsing:
CHECKPOINT, PLAN COMPLETE, SUMMARY, etc.close_agent(id) after collecting results from each agent
</codex_skill_adapter>Orchestrator role: Gather symptoms, spawn gsd-debugger agent, handle checkpoints, spawn continuations.
Flags:
--diagnose — Diagnose only. Returns a Root Cause Report without applying a fix.Subcommands: list · status <slug> · continue <slug>
</objective>
<available_agent_types> Valid GSD subagent types (use exact names — do not fall back to 'general-purpose'):
<execution_context> @$HOME/.codex/get-shit-done/workflows/debug.md </execution_context>
<context> User's input: {{GSD_ARGS}}Parse subcommands and flags from {{GSD_ARGS}} BEFORE the active-session check:
--diagnose: SUBCMD=debug, diagnose_only=true, strip --diagnose from descriptionCheck for active sessions (used for non-list/status/continue flows):
ls .planning/debug/*.md 2>/dev/null | grep -v resolved | head -5
</context>
<process>
Execute end-to-end.
</process>data-ai
Show MemPalace status — room counts, storage usage, and palace health.
tools
Search your MemPalace — semantic search across all mined memories, projects, and conversations.
tools
Mine a project or conversation into your MemPalace — extract and store memories for later retrieval.
development
Initialize a new MemPalace — guided setup for your AI memory palace with ChromaDB backend.