codex

core

Cost-tiered specialist subagents, workflow commands, guardrail + live-budget-ceiling + auto-quality hooks, a repo-bootstrap skill, a terse output style, and parity MCP servers — for serious polyglot software work.

22 on GitHubby Shekhar Mudarapuv2.4.0MITupdated 3 days agoDeveloper Tools

Plugin core in dshakes/compass. Commands read from the repo's manifest — 3 days ago.

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

What it installs

Skills (9)

  • bootstrap-agent-config

    Generate a high-quality project CLAUDE.md and AGENTS.md by inspecting the current repository. Use when a repo has no agent config, when onboarding a new project, or when the user asks to "set up Claude/Codex for this repo" or "write a CLAUDE.md". Detects languages, build/test commands, and structure

  • cost-sentinel

    Spend/cache watchdog — reads the Anthropic Admin API usage report for the last 24h and flags per-key spend over a limit, always-on keys (active 7 of 7 days), low cache-read ratio, and keys not in an allowlist of known consumers. Use weekly on a schedule or on demand when spend looks off. Read-only;

  • harden

    Run the toolkit's security commands in order to surface secrets, MCP supply-chain issues, install drift, release provenance gaps, and untrusted-code risks before shipping. Use before opening a PR, after adding a dependency, or whenever the security posture needs a fresh check.

  • morning-triage

    Discovery for an autonomous loop — find this turn's work instead of being handed it. Reads what changed since the last run (failed CI, new issues, merged commits), judges what's actually worth acting on, writes findings to a durable state file, and hands each off to the SDLC loop with a stop-conditi

  • pr-shepherd

    Take every open PR end-to-end — diagnose failing checks, classify them (real defect vs mechanical vs environmental), fix the mechanical ones on the PR branch, re-verify, and stop at the merge gate. Use on demand ("handle the open PRs") or on an interval via /loop (e.g. "/loop 15m /pr-shepherd"). Mer

  • route

    Detect the work type of a task or diff and dispatch the right specialist review/agent. Use when you're about to review or implement and want the correct domain reviewer (UI/design, API/devex, infra, docs, core) instead of a generic pass. The local mirror of the SDLC Classifier + domain-routed review

  • systematic-debugging

    Use when something is broken — a failing test, panic, stack trace, error log, or wrong behavior whose cause isn't obvious. Reproduce it, form a hypothesis, PROVE the cause before changing code, then make the minimal root-cause fix and guard it with a test. For deep cases, hand off to the debugger su

  • using-compass

    Use at the START of any task in a compass-enabled repo, or whenever you're unsure which capability fits. Indexes compass's guardrails, red-team, router, commands, subagents, and skills so you reach for the right tool instead of working ad-hoc. Read this before hand-writing config, reviewing a diff,

  • verification-before-completion

    Use before claiming ANY task done, fix verified, check passing, or PR ready. Establish how the change is checked and actually run it — tests, typecheck, lint, the local gate, or the app itself — and observe it pass. Never report "should work" or pass along a subagent's unproven claim.

Slash commands (13)

  • /core:adr

    Draft an Architecture Decision Record for a load-bearing decision

  • /core:cost

    Re-plan the current task to minimize model cost without losing quality

  • /core:onboard

    Onboard into the current repo — detect stack, install deps, get build+test green, write a grounded CLAUDE.md, and print a codebase map

  • /core:pr-shepherd

    Take every open PR end-to-end — diagnose, fix mechanical failures, stop at the merge gate

  • /core:pr

    Open a pull request with a description generated from the diff

  • /core:review

    Review the current diff for correctness, security, and conventions

  • /core:scaffold

    Scaffold a new module/service following this repo's existing conventions

  • /core:sdlc

    Run the headless SDLC pipeline (plan→build→review→audit→security→QA→PR) on a task

  • /core:ship

    Pre-ship pipeline — test, review, then prepare a clean commit

  • /core:spec

    Draft a lightweight spec / intent doc for a feature — the ground truth the build and review verify AGAINST. Use before non-trivial work; skip for one-liners. Writes a short, committed spec to specs/.

  • /core:tdd

    Test-driven change — write the failing test first, then implement

  • /core:team-review

    Review the current diff with a coordinated agent TEAM (parallel reviewers that talk to each other) instead of sequential subagents. Experimental — needs CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1.

  • /core:triage

    Triage a failing test, panic, CI failure, or error log

Subagents (15)

  • api-designer

    Designs API contracts — REST, gRPC/protobuf, and proto-first service interfaces. Use when shaping endpoints or messages, versioning a public surface, or reviewing an API for backward compatibility and devex. A wrong contract is expensive to unship, so it reasons about compatibility first.

  • architect

    Designs the implementation approach for a non-trivial feature or change before any code is written. Use for multi-file, multi-service, or ambiguous work. Produces a concrete plan, identifies risks and the files to touch, and weighs tradeoffs. Read-only — never edits.

  • code-reviewer

    Reviews a diff or set of changes for correctness, security, and convention adherence. Use proactively after writing a non-trivial chunk of code, before committing, or when the user asks for a review. Returns prioritized, actionable findings — not a rewrite.

  • db-expert

    Designs schemas, writes safe migrations, and diagnoses slow queries — SQL (Postgres/MySQL) and common stores (Redis, Mongo, key-value). Use for schema/index design, migration safety, and query-plan tuning. Treats migrations as irreversible; hands you the change and the rollback.

  • debugger

    Roots out the cause of a specific failing test, stack trace, panic, or wrong behavior. Use when something is broken and the cause isn't obvious. Forms a hypothesis, proves it, then proposes the minimal fix.

  • docs-writer

    Writes and updates documentation — READMEs, ADRs, API docs, runbooks — matching the repo's existing voice. Use to document a feature, write an ADR, or refresh stale docs. Cheap and prose-focused.

  • go-engineer

    Implements Go changes idiomatically — services, gRPC, concurrency, tests. Use for focused Go feature/bugfix work, especially control-plane / backend services. Writes code and tests, runs vet and tests before handing back.

  • k8s-operator

    Diagnoses Kubernetes/cluster state and drafts manifest changes (Kustomize/Helm/ArgoCD). Use to investigate failing pods, read cluster state, or prepare deployment changes. Reads freely; never applies or deletes — it hands you the change to run.

  • perf-profiler

    Profiles slow or resource-heavy code and fixes the real bottleneck — latency, throughput, CPU, memory, allocations. Use when something is slow (not broken), before/after a suspected regression, or to validate an optimization with numbers. Measures first, changes one thing, measures again.

  • python-engineer

    Implements Python changes idiomatically — 3.11+, full type hints, pydantic/dataclasses, tests. Use for focused Python feature/bugfix work, especially services, data pipelines, and ML/inference glue. Writes code and tests, runs ruff and tests before handing back.

  • rust-engineer

    Implements Rust changes idiomatically — hot-path services, async, error handling, tests. Use for focused Rust feature/bugfix work, especially latency-sensitive gateway/router/runtime code. Writes code and tests, runs clippy and tests before handing back.

  • security-auditor

    Deep security review of changes or a component — authz, secrets, injection, trust boundaries, crypto, multi-tenancy. Use when touching auth, encryption, tenant isolation, external inputs, or before shipping security-sensitive code. Read-only.

  • test-architect

    Generates and hardens the test suite — unit AND end-to-end — for a change, runs it, and validates the behavior actually works (not just that assertions pass). Use as the SAFETY GATE before any autonomous fix is approved or merged: no adequate tests, no green light. The thing that makes the autonomou

  • test-runner

    Runs the test suite (or a subset), parses failures, and reports a tight summary with root-cause hypotheses. Use to execute tests and triage failures without spending driver-model tokens. Does not fix code unless asked.

  • typescript-engineer

    Implements TypeScript/Node changes idiomatically — strict types, discriminated unions, zod at boundaries, tests. Use for focused TS/JS feature/bugfix work, especially typed backends, SDKs, and server/client boundaries. Writes code and tests, runs typecheck and lint before handing back.

MCP servers (3)

  • context7

    runs: npx -y @upstash/[email protected]

  • fetch

    runs: uvx --from mcp-server-fetch==2025.4.7 mcp-server-fetch

  • git

    runs: uvx --from mcp-server-git==2026.1.14 mcp-server-git

Hooks (9)

  • SessionStart

    "${CLAUDE_PLUGIN_ROOT}"/hooks/inject-context.sh

  • SessionStart

    "${CLAUDE_PLUGIN_ROOT}"/hooks/scan-untrusted-context.sh

  • UserPromptSubmit

    "${CLAUDE_PLUGIN_ROOT}"/hooks/scan-prompt.sh

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}"/hooks/protect-paths.sh

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}"/hooks/budget-gate.sh

  • PostToolUse

    "${CLAUDE_PLUGIN_ROOT}"/hooks/format-on-edit.sh

  • PostToolUse

    "${CLAUDE_PLUGIN_ROOT}"/hooks/scan-tool-output.sh

  • Stop

    "${CLAUDE_PLUGIN_ROOT}"/hooks/notify.sh

  • Notification

    "${CLAUDE_PLUGIN_ROOT}"/hooks/notify.sh

View source on GitHub dshakes.github.io

More from dshakes/compass

All 3 plugins →

compass

claudecodex

15 specialist subagents; 13 commands (/ship /review /tdd /pr /adr /triage /scaffold /cost /onboard /spec /sdlc /team-review /pr-shepherd); guardrail + red-team + live-budget-ceiling + format-on-edit + notify hooks (a per-session dollar cap that hard-stops the agent, not just warns); 9 skills (using-compass, bootstrap-agent-config, harden, route, morning-triage, cost-sentinel, pr-shepherd, verification-before-completion, systematic-debugging); a Concise output style; and version-pinned context7/fetch/git MCP servers (context7 reaches Upstash; fetch makes outbound HTTP).

9 skills · 13 commands · 15 agents · 3 MCP servers · hooks

22

core-lsp

claude

Opt-in language-server intelligence (diagnostics + navigation) for Go, Rust, TypeScript, and Python. Requires gopls/rust-analyzer/typescript-language-server/pyright on PATH.

LSP

22

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

CMEM Pro

claude

CMEM Pro for the Claude app - hooks stream tool use to cmem.ai and inject observations into new sessions and agents

3 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

mempalace

claudecodex

AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.

3 skills · 6 commands · 1 MCP server · hooks

MemPalace/mempalace 60,536

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

Maintain core?

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 plugins3 plugins