Agent Claude Code
Write-and-run research sub-agent for orchestrated plans, sibling of the investigator. Answers open-ended research questions that read-only investigation cannot answer by writing and running code in the session scratchpad ONLY and by searching/fetching the web, then returns findings and their evidence within a hard…
Agent Claude Code
Propose-only garbage-collection sub-agent for an orchestrated plan's state file. Reads the state file, its dated archives and the retained handbacks, then RETURNS retire / condense / promote batches pre-formatted in the state table shape, each carrying its "replaces ; archive: " marker. Writes nothing outside the…
Agent Claude Code
Read-only investigation sub-agent for orchestrated plans. Searches corpora, reads long files, reproduces defects and surveys options, then returns findings and their evidence within a hard output budget. Writes nothing outside the session scratchpad, never writes a plan's state file or a handback, and never runs a…
Agent Claude Code
Self-improvement sub-agent for the portable workflow harness. Reads the corpus (commands/, agents/, harness/, hooks/) before editing, makes exactly one targeted change per invocation, never touches preferences.md, commits its edit in the harness repo (and pushes harness main when committing on main, keeping the public…
Command Claude Code
In-place install/upgrade step for the portable workflow harness. Generates the per-project scaffolding around the portable tree already present at .claude/ (from a git clone or an extracted zip): .claude/preferences.md from the single template, a root CLAUDE.md from the skeleton template, docs/ + context/ directories…
Command Claude Code
Lightweight grill-then-build for tasks too small for a full plan. Runs a mixed-style grilling capped at 8 questions, writes a short brief to docs/quick/ brief.md, gates go/no-go via AskUserQuestion, then implements in-session. Standalone it ends in a quick/ PR the user merges; handed a prompt carrying an "##…
Command Claude Code
Run a structured requirements session in one of three modes (mixed default, functional, technical), then produce a PRD and multi-phase implementation plan. Requires docs/ folder with subdirs prds/, multiphaseplans/, learnings/, prompts/ -- created by /bootstrap.
Command Claude Code
Write Jira tickets and a standup update for all work done on a given date.
Command Claude Code
The single onboarding funnel for a new harness recipient -- the one command to type after cloning or unzipping the harness into a project. Verifies prerequisites (git repo, gh auth, python interpreter with a permission-gated install offer), detects the install tier (clone vs zip), invokes /bootstraptocustomcommands to…
Command Claude Code
Drive a long-running, progressively-disclosed plan from a single durable state file. The same invocation initialises a new plan or resumes an existing one, writes state through before replying, dispatches one session at a time on the user's word, and ingests each session's handback. On the user's ask, a live…
Command Claude Code
Compile a reference-based phase implementation prompt (200 lines) from a plan's PRD, phase section, accumulated learnings, and the harness procedure files.
Agent Claude Code
Jira sub-agent that searches, creates, updates, comments on and transitions issues through the Atlassian MCP server on the caller's instruction, then reports every key and URL it touched. Reads the project's Jira parameters from the preferences key block; never gates writes on a preview (sub-agents cannot ask the…
Command Claude Code
Orchestrated-only requirements grilling: open a lean handback stub, grill via AskUserQuestion with no question cap until the user says "stop asking questions", then write a full requirements doc and finalize the lean handback. No branch, no commits; writes only gitignored docs files.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: