spec-driven-development agents

ariel-frischer/autospec

Command Claude Code

Execute the implementation plan by processing tasks defined in tasks.yaml.

cowwoc/cat

Plugin Claude Code

Plugin marketplace listing 1 plugin: cat.

cowwoc/cat

Settings file Claude Code

Agent settings declaring 1 hook event (PreToolUse).

cowwoc/cat

Instructions file

Claude Code instructions for cowwoc/cat, covering project instructions, commit types for plugin files, plugin development and testing requirements.

cowwoc/cat

Command

Clean up abandoned worktrees, lock files, and orphaned branches.

cowwoc/cat

Command

Analyze and learn from mistakes.

cowwoc/cat

Command

Display project progress - versions, tasks, and completion status.

cowwoc/cat

Hook

Runs when a session starts, executing check-upgrade.sh, check-update-available.sh, echo-session-id.sh, check-retrospective-due.sh and inject-session-instructions.sh (5 commands). From cowwoc/cat.

cowwoc/cat

Hook

Runs when you submit a prompt, before the agent sees it, executing get-skill-output.py and detect-giving-up.sh via python3 (2 commands). From cowwoc/cat.

cowwoc/cat

Hook

Runs after a tool call finishes for Bash, Write, Edit, Read, Glob, Grep, WebFetch and WebSearch tool calls, executing get-posttool-output.py, detect-assistant-giving-up.sh, get-bash-posttool-output.py, remind-restart-after-skill-modification.sh and get-read-posttool-output.py via python3 (5 commands). From cowwoc/cat.

cowwoc/cat

Skill Claude CodeCodex

Compare two documents semantically with relationship preservation to identify content and structural differences.

cowwoc/cat

Skill Claude CodeCodex

Analyze mistakes with conversation length as potential cause (CAT-specific).

cowwoc/cat

Skill Claude CodeCodex

Use BEFORE creating or updating any skill OR command - decomposes goal into forward steps via backward reasoning.

attilaszasz/sdd-pilot

Skill Claude CodeCodex

Propagate a bootstrap change across canonical project artifacts and the project plan. Direct command-bar dispatch only; do not select for general queries.

attilaszasz/sdd-pilot

Skill Claude CodeCodex

Run the full SDD feature-delivery pipeline. Direct command-bar dispatch only; do not select for general queries.

attilaszasz/sdd-pilot

Skill Claude CodeCodex

Run implement and QC in a continuous loop. Direct command-bar dispatch only; do not select for general queries.

attilaszasz/sdd-pilot

Settings file Claude Code

Agent settings declaring 69 allowed tools.

attilaszasz/sdd-pilot

Agent

Creates, amends, and supersedes standalone MADR ADR files under specs/adrs/ and prepares sad.md ADR catalog updates.

attilaszasz/sdd-pilot

Agent

Detects the current feature branch, derives the feature directory, validates prerequisites, and returns structured context for other SDD Pilot agents.

attilaszasz/sdd-pilot

Agent

QC sub-agent. Executes tests, static analysis, and security tools. Asks user for permission before installing missing dependencies.

alfredoperez/speckit-companion

Command Claude Code

Score the 2 bench variant folders for one size (build/acceptance/regression/conventions/capture + rubric + cross-solution review), record, report, and reset.

alfredoperez/speckit-companion

Command Claude Code

Autonomously fix one or more speckit-companion GitHub issues with the SpecKit Companion pipeline — clean branch, fix, review, PR, merge, reinstall — then write a manual-verification report. Self-hosting build loop.

alfredoperez/speckit-companion

Command Claude Code

Ship an ALREADY-BUILT ticket — code review → PR → merge → learnings → install-local. Skips the build (you built it in SpecKit Companion). The tail of /fix-tickets, no rebuild.

alfredoperez/speckit-companion

Skill Claude CodeCodex

Evaluate the speckit-extension end-to-end against a real spec — verify lifecycle hooks fired, .spec-context.json captured each step into canonical history[], timing is real (not backfilled), and per-task execution was journaled. Umbrella eval for the spec-kit-side extension; grows as features land (auto-mode, etc.).…