vrennat
01Plugin Claude Code
Plugin marketplace listing 1 plugin: developersDevelopers.
Plugin Claude Code
Plugin marketplace listing 1 plugin: developersDevelopers.
Plugin Claude Code
Lean, opinionated workflow plugin for Claude Code. Replaces obra/superpowers with confirm-only-when-ambiguous routing.
Agent
Independent break-it review for high-stakes changes (auth, money, data, security, privacy, hard-to-undo). Reads source fresh and hunts the traps self-review misses. Use when /impl flags a change high-stakes, regardless of file count.
Agent
Thorough code review for risky or architectural changes. Use when /impl touches >5 files, security-sensitive code, or shared infrastructure. Identifies real problems; does not nitpick style.
Agent
Deep bug investigation when validator fails or behavior is unexplained. Forms hypotheses, runs minimal experiments to verify, identifies root cause. Use when fast-impl's first attempt didn't work and the cause is not obvious.
Agent
Execute well-defined implementation tasks quickly and without deliberation. No architectural judgment, no scope expansion.
Agent
Run quality gates after implementation. Typecheck, tests, lint. Verify requirements are met and check for obvious issues. Fast and mechanical. Use after fast-impl completes work, before any code review.
Command
Bootstrap a project to use developersDevelopers. Creates docs/specs and docs/plans, detects legacy obra/superpowers paths, prints copy-paste commands for migration and templates. Idempotent. Named bootstrap (not init) to avoid colliding with Claude Code's built-in /init.
Command
Idea -> spec doc. Lean: clarifying questions only when ambiguous, default to recommendation, no per-section approval gates. Output to docs/specs/.
Command
Audit the repo for dD: routing-decision markers and print a ledger grouped by file, flagging entries that name no upgrade trigger. Use to review accumulated deliberate-shortcut debt left by /impl. Read-only; never edits or removes markers.
Command
Workhorse command. Spec file, ticket ID, or freeform description -> classified, routed, executed work. Confirms only when ambiguous. Auto-detects Linear MCP for ticket flows.
Command
Set how aggressively the workflow confirms before acting — cautious, default, or autonomous. Stored at .claude/dd-mode and read by the SessionStart hook and /impl. With no argument, reports the current mode.
Command
Spec -> written implementation plan. Opt-in. Use only when you want to review a plan before executing. Most work skips this and goes straight to /impl.
Command
Opt-in, explicit /research invocation only. Measurable experimentation loop that sets up a .lab/ directory and runs THINK -> TEST -> REFLECT iterations. Does not auto-trigger on experimentation-shaped asks; use only when the user types /research.
Command
Strict RED-GREEN-REFACTOR scaffold. Opt-in. Use when you want full TDD discipline. Not an always-on behavior.
Command
Deletion-focused code review. Hunts only what to remove — over-engineering, dead flexibility, reinvented stdlib, speculative abstraction. Not correctness, not security (those are brutal-code-reviewer and adversarial-reviewer). Outputs one line per finding plus a net line-savings total.
Hook
Runs when a session starts on startup, resume, clear and compact, executing session-start.js via node. From vrennat/developersDevelopers.
Skill Claude CodeCodex
Use when user mentions installing, configuring, or starting a project with developersDevelopers, or asks how to migrate from obra/superpowers. Surfaces the /bootstrap bootstrap command.
Skill Claude CodeCodex
Tournament-style planning that produces one polished plan from an idea by drafting from four lenses (MVP-first, risk-first, dependency-first, user-first) in parallel, scoring with four judges, and synthesizing the winner with grafted moves from runner-ups. Use when the user asks for a substantive implementation plan…
Skill Claude CodeCodex
Use when Claude observes a real error, test failure, or unexpected runtime output during execution. Forms hypothesis, runs minimal experiment, iterates to root cause before any fix.
Skill Claude CodeCodex
Use when about to claim work is complete, fixed, passing, or ready. Requires running the verification command and showing its output before any success claim.