golem15/msd-core
4
0
Fork 0
Code Issues 1 Pull Requests Actions 3 Packages Projects Releases Wiki Activity

docs(workflows): address CodeRabbit markdownlint and wording findings

Browse Source
This commit is contained in:
Tom Boucher
2026-05-06 15:30:28 -04:00
parent e53c5e6865
commit a4cb7451ff
5 changed files with 10 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
get-shit-done/workflows/code-review-fix.md
View File

@@ -188,7 +188,7 @@ echo "Fix scope: ${FIX_SCOPE}"
Use Agent() to spawn agent: Use Agent() to spawn agent:
``` ```text
Agent(subagent_type="gsd-code-fixer", prompt=" Agent(subagent_type="gsd-code-fixer", prompt="
<files_to_read> <files_to_read>
${REVIEW_PATH} ${REVIEW_PATH}

4
get-shit-done/workflows/execute-phase.md
View File

@@ -480,7 +480,7 @@ increases monotonically across waves. `{status}` is `complete` (success),
creation before the next begins (the round-trip latency of each tool call provides creation before the next begins (the round-trip latency of each tool call provides
natural spacing), while all agents still **run in parallel** once created. natural spacing), while all agents still **run in parallel** once created.
``` ```text
# CORRECT: dispatch one Agent() per message, each with run_in_background: true # CORRECT: dispatch one Agent() per message, each with run_in_background: true
# → worktrees created sequentially, agents execute in parallel # → worktrees created sequentially, agents execute in parallel
# #
@@ -488,7 +488,7 @@ increases monotonically across waves. `{status}` is `complete` (success),
# → simultaneous git worktree add → .git/config.lock contention → failures # → simultaneous git worktree add → .git/config.lock contention → failures
``` ```
``` ```text
Agent( Agent(
subagent_type="gsd-executor", subagent_type="gsd-executor",
description="Execute plan {plan_number} of phase {phase_number}", description="Execute plan {plan_number} of phase {phase_number}",

2
get-shit-done/workflows/new-milestone.md
View File

@@ -340,7 +340,7 @@ Use template: ~/.claude/get-shit-done/templates/research-project/{FILE}
After all 4 complete, spawn synthesizer: After all 4 complete, spawn synthesizer:
``` ```text
Agent(prompt=" Agent(prompt="
Synthesize research outputs into SUMMARY.md. Synthesize research outputs into SUMMARY.md.

2
get-shit-done/workflows/new-project.md
View File

@@ -920,7 +920,7 @@ Use template: ~/.claude/get-shit-done/templates/research-project/PITFALLS.md
After all 4 agents complete, spawn synthesizer to create SUMMARY.md: After all 4 agents complete, spawn synthesizer to create SUMMARY.md:
``` ```text
Agent(prompt=" Agent(prompt="
<task> <task>
Synthesize research outputs into SUMMARY.md. Synthesize research outputs into SUMMARY.md.

10
get-shit-done/workflows/plan-phase.md
View File

@@ -866,9 +866,9 @@ Every task MUST include these fields — they are NOT optional:
</quality_gate> </quality_gate>
``` ```
**If `CHUNKED_MODE` is `false` (default):** Spawn the planner as a single long-lived Task: **If `CHUNKED_MODE` is `false` (default):** Spawn the planner as a single long-lived Agent:
``` ```text
Agent( Agent(
prompt=filled_prompt, prompt=filled_prompt,
subagent_type="gsd-planner", subagent_type="gsd-planner",
@@ -885,9 +885,9 @@ Agent(
**Skip if `CHUNKED_MODE` is `false`.** **Skip if `CHUNKED_MODE` is `false`.**
Chunked mode splits the single long-lived planner Task into a short outline Task followed by Chunked mode splits the single long-lived planner Agent run into a short outline Agent run followed by
N short per-plan Tasks. Each Task is bounded to ~3–5 min; each plan is committed individually N short per-plan Agent runs. Each run is bounded to ~3–5 min; each plan is committed individually
for crash resilience. If any Task hangs and the terminal is force-killed, rerunning for crash resilience. If any run hangs and the terminal is force-killed, rerunning
`/gsd-plan-phase {N} --chunked` resumes from the last successfully committed plan. `/gsd-plan-phase {N} --chunked` resumes from the last successfully committed plan.
**Intended for new or in-progress chunked runs.** To recover plans already written by a prior **Intended for new or in-progress chunked runs.** To recover plans already written by a prior