marketplace
01Plugin Claude Code
SpecSwarm: complete software development toolkit. Spec-driven workflows, autonomous orchestration, lifecycle management Build->Modify->Fix->Ship.
Plugin Claude Code
SpecSwarm: complete software development toolkit. Spec-driven workflows, autonomous orchestration, lifecycle management Build->Modify->Fix->Ship.
Instructions file
Instructions for MartyBonacci/specswarm, covering claude.md — specswarm, subagent model specialization (v7.7.0), development, plugin validation (required before commits) and version bumping.
Plugin Claude Code
DEPRECATED — SpecSwarm commands have moved to the ss plugin. Install ss@specswarm-marketplace and uninstall this plugin. Slated for full removal in v8.0.0.
Plugin Claude Code
SpecSwarm status line: a rich Claude Code statusline (directory, git, model, context, rate limits, session usage) plus a real-time background-builder segment for SpecSwarm conduct dispatches — answers 'is it safe to close / shut down?' at a glance, no daemon needed. Wraps your existing statusline if you have one.…
Command
One-time install of the SpecSwarm status line. Preserves and wraps your existing statusline if you have one (it becomes the cached base), adds the real-time background-builder segment (🔨 building / 💀 died / ✓ safe to close), and sets a refreshInterval so status updates even while the session is idle. Fully…
Command
Restore the statusline configuration exactly as it was before /ss-status:install — the saved original statusLine settings entry is put back (or removed, if none existed before).
Plugin Claude Code
SpecSwarm: complete software development toolkit. Spec-driven workflows, multi-agent orchestration, lifecycle management Build->Modify->Fix->Ship. Commands available at /ss:.
Agent
Synthesizes durable memory entries from a completed SpecSwarm chunk's signals — commits, final tasks.md, verify-queue outcomes (PASS/DRIFT), captured interventions, AskUserQuestion answers. Use at /ss:ship time (or just before) to capture the cross-chunk lessons that would otherwise live only in session history and…
Agent
Polishes raw decision-candidate signals from a SpecSwarm plan.md into a small, well-formed batch of strategic decisions for AskUserQuestion. Use after /ss:plan completes and before /ss:tasks runs. Reads plan.md, tech-stack.md, constitution.md, quality-standards.md (locked prior commitments), and a TSV list of…
Agent
Predicts what a SpecSwarm chunk's execution would look like WITHOUT running it. Use after /ss:specify (or any later phase) to surface anticipated decisions, risk register, out-of-scope guards, memory gaps, touchpoint estimate, and predicted artifacts. Reads spec.md plus foundation files plus memory plus intervention…
Agent
Multi-agent orchestration specialist for SpecSwarm. Analyzes tasks.md, identifies parallelizable work streams, routes tasks to specialist agents, and creates integration manifests. Use during implementation phase when --orchestrate flag is set.
Agent
Adversarial verification agent for SpecSwarm tasks. Use when a task has just been marked complete and you need a fresh-context, judgment-grade check that the implementation matches the spec verbatim. Compares git diff against §-referenced spec sections + plan.md task block + memory files; returns PASS, DRIFT (with…
Agent
Routes tasks to specialist agents based on content keyword analysis. Used by the orchestrator for multi-agent builds.
Command
Comprehensive codebase quality analysis with prioritized recommendations.
Command
Calibration loop for taste-heavy choices (v7.16.0). Generates N candidate implementations/outputs, renders a side-by-side contact sheet, captures your verdict, pins the winner with a regression test, and distills the ruling into the taste model. Converts fuzzy judgment into deterministic constants.
Command
Regression-test-first bug fixing workflow with smart SpecSwarm/SpecTest integration.
Command
Command "build" from MartyBonacci/specswarm, covering user input, goal, pre-flight checks, pre-flight a: parse arguments and parse arguments.
Command
Assume-first gap resolution for the current feature spec (v7.13.0). Auto-fills gaps resolvable from the taste model, spec corpus, or codebase precedent — recorded as provenance-cited entries in the spec's ASSUMPTIONS section — and asks only genuine forks, batched. Reviewing assumptions is 5× faster for a human than…
Command
Complete feature or bugfix workflow and merge to parent branch.
Command
Mentor→builder headless dispatch loop (v7.18.0). Author a slice prompt in the proven grammar, dispatch it to a headless builder in the target repo (opus-pinned, per-tree locked, group-killed on timeout, fully audited), then run the INDEPENDENT verification protocol — commit-hash check, real-diff read, targeted gates …
Command
Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in sync.
Command
Pre-batch all strategic decisions for a feature into one AskUserQuestion-driven sheet, BEFORE /ss:tasks runs. Collapses the mid-chunk "wait, decide this" interrupts into a single front-loaded touchpoint. Hybrid deterministic-scan + decision-miner subagent; writes decision-sheet.md and appends a locked Pre-Batched…
Command
Predict what a SpecSwarm chunk's execution would look like WITHOUT running it. Phase-aware — detects which artifacts exist, simulates everything still ahead. Produces a structured dry-run.md with anticipated decisions, risk register, out-of-scope guards, memory gaps, touchpoint estimate, predicted artifacts.…
Command
Command "fix" from MartyBonacci/specswarm, covering user input, goal, pre-flight checks, parse arguments and extract bug description (first non-flag argument).