claudecodex

dev-kit

AI-native single plugin absorbing the dev-harness family (pm-prd-fast + interview-harness + dev-harness + claude-review-plugins + slop-shield). A2A typed, Eval-Repair loop, Human-on-the-Loop.

1 on GitHubby sangheev0.3.350MITupdated 1 month ago
/

Plugin dev-kit from marketplace dev-kit in sh-ai-x/dev-harness-kit. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (47)

  • babysit-pr-local

    0-arg local-mode PR babysitter. Pre-push pytest gate + local LLM judge verdict loop; replaces `gh pr checks --watch` with `bin/review-local.sh`.

  • babysit-pr

    0-arg restart-safe PR check, diagnose, fix, and hand-off loop.

  • bootstrap

    0-arg setup for CLAUDE.md, AGENTS.md, hooks, and optional CI.

  • bump

    Explicit version bump of `.claude-plugin/plugin.json` + push of `chore/bump-vX.Y.Z`. Mirrors the auto-bump in `.github/workflows/version-bump.yml` but user-triggered for race recovery and pre-PR explicit bumps. For catching a branch up to origin/main (==, not +1) use `/dev-kit:sync-version` instead.

  • ci-doctor

    Read-only CI readiness audit. Prints one PASS/FAIL summary across files, marker, provider file, secrets, and gh auth. Hand-off answer to "would CI succeed on my next PR?

  • ci-setup

    Install dev-kit's reusable CI workflow templates into a target project. Idempotent via `.dev-kit/ci-config.json` presence, no version gate. Hand-off to /dev-kit:build.

  • ci-triage

    Triage failing GitHub Actions runs across recent commits, dedupe against a persisted case store, judge new failures against a model/context/harness taxonomy with a required repro + regression test, and record them without re-analyzing repeats.

  • ci-update

    Detect + selectively apply drift between installed CI templates and current dev-kit source. 4-state per-file classification with backup-before-overwrite.

  • codex-cache-update

    Refresh the dev-kit Codex marketplace checkout and synchronize the versioned plugin cache. Use when Codex reports the marketplace is current but the installed cache may be stale, or after a dev-kit merge.

  • config

    skill + hook + methodology picker (multiSelect).

  • cost-gate

    0-arg cost-gate status. Prints current session spend, threshold distance, and a two-line git-trailer block to include in commits so the PR-level cost flag can aggregate.

  • docs-maintenance

    Audit repository documentation with the project README as the highest-priority document. The README is always audited AND verified every run, and updated when needed.

  • evaluate

    0-arg eval extension. Replays transcripts and consumes workflow evidence against registered rubrics, preserving legacy Agent Behavior D1–D7 and reporting five harness-effectiveness components plus the nested measurement-integrity submetric (issue #663). /dev-kit:evaluate.

  • evidence-plan

    Idea → cited research → HTML proposal (human confirms) → /dev-kit:plan hand-off. The proposal is rendered and reviewed BEFORE the expensive 5-gate PRD work runs, not after.

  • gate-artifacts

    Create or delete managed GitHub Actions gate artifacts backed by gates.json.

  • gate-select

    Unified 3-dimension picker for project / session / AI-judge gates. Reads .dev-kit/gates.json + .dev-kit/ci-config.json + .dev-kit/harness-mode.session.json and dispatches writes through `python -m lib.gates_state ...`.

  • guard-mode

    Session-scoped on/off toggle for the tdd-guard, worktree-guard, and git-guard hard-block hooks.

  • harness-effectiveness

    0-arg harness-effectiveness report. Wraps `lib.harness_effectiveness.build_report` and prints the four-component (prevention / first-pass / recovery / measurement-integrity) scorecard as JSON + a one-line status verdict. The measurement-integrity component also reports a nested stability submetric (

  • harness-mode

    Session-scoped local-hook mode picker — fast (all optional local hooks off), full (default, all on), or custom (interactive per-local-hook picker via AskUserQuestion).

  • hook-doctor

    Diagnose failed Claude Code or Codex hooks, repair safe cache and registration drift, and report the exact restart step.

  • inspect

    0-arg read-only code health audit. 8-dim fan-out (dead, dup, smell, overeng, overarch, cleancode, tokenbudget, slop) + --secrets/--slop aliases to the audit family (lib/analysis_core/dimensions.py).

  • interview

    5-field safety-contract interview that gates plan emission. Drives `lib.interview_engine` through one Ralph loop, enforces `safety_valve=8`, `narrowed_delta`, `dedup_metric` (identical-ambiguity-cycle=2), and `user_interrupt`.

  • linear

    Optional Linear task tracker. Reconcile the current repository task with a canonical project and non-duplicate issue. Auto-syncs on every Claude Code edit when configured. Owner-gated auto-triggers also fire on worktree create, session start, and task change. Supports a hard lock (`linear lock`) tha

  • llm-refresh

    Refresh docs/llm-info/<provider>.json from each vendor's official pricing page via WebFetch extraction. Diff-then-commit; manual like set-provider.sh.

  • log

    Toggle /log setup|on|off|status — install/remove loghooks from ~/dev/loghooks into the current project's Claude/Codex settings.

  • maintenance

    Code-sanity gate. Judges the PR diff against the 20-checkbox rubric from eval/prompts/judge-code-sanity.md (CC-1..8 clean code, OE-1..8 over-engineering, VM-1..4 value/meaning). Mirrors .github/workflows/maintenance.yml's gate logic. Verdict mapping: code_sanity_score >= 8.0 -> Approve; 5.0..7.99 ->

  • mode

    Read or write the active DEV_KIT_MODE (full | lite | undev) for the current project. Picker by default; --show to display current mode; --scope=local to write to .claude/settings.local.json instead of .claude/settings.json.

  • plan

    0-arg plan stage. Take 1-line idea → PRD.md + phases/<name>/{index.json, step<N>.md} in 5 gates. Quantified value (cost/LTV) + ambiguity loop (0-10) replace the old 5-question grill-me.

  • pr-verify

    Deterministic PR verification — fresh `gh pr view` + check + comment fetches on every call. Catches the "stale CI / LLM-judge still in progress" false positive the babysit flow had.

  • proposal-orch-issue-pr

    0-arg orchestrator-first GitHub backlog triage. Gathers open PRs + issues, scores (bottleneck / risk / change containment), orders by orchestrator critical path, and writes a proposal YAML + HTML via the existing `/dev-kit:proposal` renderer.

  • proposal

    0-arg YAML-to-HTML renderer for reviewable design proposals.

  • prune-propose

    0-arg skill — usage telemetry dump + per-skill delete proposal. User approves each deletion explicitly.

  • prune

    0-arg slop-removal chain. One slash wraps inspect → 3-pass delete sweep → review. Gated phases for deleting AI slop and dead features (not refactoring).

  • ralph

    End-to-end autonomous loop with 4 user gates + unattended build/babysit/ship.

  • refactor

    0-arg cleanup chain. One slash wraps inspect -> cleanup -> review. 3 gated phases with quoted exit codes between each.

  • research

    0-arg research gate. Run Phase 0-3 escalation (cache / direct / multi / human) + verify() + enforce_citations(). /dev-kit:research <claim> [--max-phase N].

  • review-local

    Local equivalent of the GH-Actions review workflow. Runs /dev-kit:review + /dev-kit:security + /dev-kit:maintenance (via local `claude` CLI) with the same verdict extraction + combined gate + L3-evidence enforcement + optional auto-approve as `.github/workflows/review.yml`. Saves Action minutes when

  • review

    Parallel multi-dimension code review with a false-positive filter. Fans out to per-dim experts (correctness, security, architecture) that run in parallel and return evidence-backed findings; a verifier pass confirms/rejects each candidate before rendering per-line inline comments plus a PR-style sum

  • security-metrics

    Calculate a deterministic 0-100 security scorecard for the current repository and render an evidence-backed Markdown table for OWASP Top 10 categories.

  • security

    Security fan-out — OWASP Top 10 2025 (A01–A10) plus a separate LLM01 Prompt Injection dimension. Eleven parallel subagents, one per category, return evidence-backed findings; a verification pass confirms or rejects each before a per-category breakdown table + verdict.

  • ship

    0-arg. Release tag emit. Gate check only (hooks auto). Requires Review verdict=Approve + main-block pass.

  • skill-usage

    Run the skill usage telemetry CLI and inspect turns, invocations, and per-project usage.

  • sot-harness-writer

    Interview-based Single Source of Truth harness document writer (5 rounds × 2-3 evidence-backed recommendations, full traceability, hands off to /dev-kit:plan).

  • status

    HOTL visualization. Current loop progress + cumulative cycles + hand-off chain + eval score on one screen.

  • team

    Read or write the team collaboration toggle (DEV_KIT_TEAM on|off). Default OFF, independent of DEV_KIT_MODE. When ON, team roles/dependency-aware planning is enabled and .dev-kit/ stays tracked in git.

  • token-analyzer

    0-arg token-efficiency dashboard. Runs tools/token_efficiency_analyzer.py over logs/{claude-code,codex}/*.jsonl to produce an HTML report (+ lazy per-worktree transcript sidecars) -- 4-dim session scoring, 6 anti-pattern warnings, USD savings estimate.

  • worktree-prune

    0-arg interactive prune of stale worktrees. Counts registered worktrees, lists them oldest-first by branch-tip age, asks how many to remove, then dispatches `bin/worktree-remove-safe.sh` per row after a y/N gate.

Subagents (1)

  • worktree-janitor

    Proactively audits .worktrees/* against merged/closed branches and uncommitted state. Reports removal candidates — never deletes.

Hooks (22)

  • PreToolUse

    DEV_KIT_AGENT=claude-code bash ${CLAUDE_PLUGIN_ROOT}/hooks/tdd-guard.sh

  • PreToolUse

    DEV_KIT_AGENT=claude-code bash ${CLAUDE_PLUGIN_ROOT}/hooks/worktree-guard.sh

  • PreToolUse

    bash ${CLAUDE_PLUGIN_ROOT}/hooks/linear-autosync.sh

  • PreToolUse

    DEV_KIT_AGENT=claude-code bash ${CLAUDE_PLUGIN_ROOT}/hooks/bash-guard.sh

  • PreToolUse

    DEV_KIT_AGENT=claude-code bash ${CLAUDE_PLUGIN_ROOT}/hooks/git-guard.sh

  • PreToolUse

    DEV_KIT_AGENT=claude-code bash ${CLAUDE_PLUGIN_ROOT}/hooks/review-yml-isolation.sh

  • PreToolUse

    DEV_KIT_AGENT=claude-code bash ${CLAUDE_PLUGIN_ROOT}/hooks/pr-create-route.sh

  • PreToolUse

    DEV_KIT_AGENT=claude-code bash ${CLAUDE_PLUGIN_ROOT}/hooks/destructive-confirm.sh

  • PreToolUse

    bash ${CLAUDE_PLUGIN_ROOT}/hooks/ralph-attended-lock.sh

  • UserPromptSubmit

    bash ${CLAUDE_PLUGIN_ROOT}/hooks/worktree-auto-cut.sh

  • UserPromptSubmit

    bash ${CLAUDE_PLUGIN_ROOT}/hooks/linear-task-change.sh

  • UserPromptSubmit

    bash ${CLAUDE_PLUGIN_ROOT}/hooks/context-window-guard.sh

  • SessionStart

    DEV_KIT_AGENT=claude-code bash ${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh

  • PostToolUse

    DEV_KIT_AGENT=claude-code bash ${CLAUDE_PLUGIN_ROOT}/hooks/secret-scan.sh

  • PostToolUse

    DEV_KIT_AGENT=claude-code bash ${CLAUDE_PLUGIN_ROOT}/hooks/slop-detector.sh

  • PostToolUse

    bash ${CLAUDE_PLUGIN_ROOT}/hooks/linear-worktree-create.sh

  • PostToolUse

    bash ${CLAUDE_PLUGIN_ROOT}/hooks/injection-content-guard.sh

  • PostToolUse

    bash ${CLAUDE_PLUGIN_ROOT}/hooks/injection-content-guard.sh

  • Stop

    DEV_KIT_AGENT=claude-code bash ${CLAUDE_PLUGIN_ROOT}/hooks/trace-session-end.sh

  • Stop

    bash ${CLAUDE_PLUGIN_ROOT}/hooks/stop-verify.sh

  • Stop

    bash ${CLAUDE_PLUGIN_ROOT}/hooks/worktree-session-cleanup.sh

  • SessionEnd

    DEV_KIT_AGENT=claude-code bash ${CLAUDE_PLUGIN_ROOT}/hooks/trace-session-end.sh

View source on GitHub

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

ecc

claudecodex

Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses

200 skills · 98 commands · 71 agents · 1 MCP server · hooks

affaan-m/ECC 302,088

agent-skills

claudecodex

Production-grade engineering skills covering every phase of software development: spec, plan, build, verify, review, and ship.

25 skills · 4 agents

addyosmani/agent-skills 116,782

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

ruvnet/ruflo 81,589

marketing-skills

claudecodex

53 marketing skills for technical marketers and founders: CRO, copywriting, cold email, prospecting, SEO, AI SEO, paid ads, SMS, ad creative, video production, image generation, co-marketing, churn prevention, pricing, referrals, revenue operations, sales enablement, customer research, site architecture, comprehensive AARRR-structured marketing plans, public relations and earned media, offer design, event marketing and webinars, and more

53 skills

coreyhaines31/marketingskills 59,996

Maintain dev-kit?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted