sdlc
25Command
Run the headless SDLC pipeline (plan→build→review→audit→security→QA→PR) on a task.
Command
Run the headless SDLC pipeline (plan→build→review→audit→security→QA→PR) on a task.
Command
Pre-ship pipeline — test, review, then prepare a clean commit.
Command
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/.
Command
Test-driven change — write the failing test first, then implement.
Command
Review the current diff with a coordinated agent TEAM (parallel reviewers that talk to each other) instead of sequential subagents. Experimental — needs CLAUDECODEEXPERIMENTALAGENTTEAMS=1.
Command
Triage a failing test, panic, CI failure, or error log.
Skill Claude CodeCodex
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, then drafts…
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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-condition. Use as the…
Skill Claude CodeCodex
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"). Merges only when the…
Skill Claude CodeCodex
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 reviewers.
Skill Claude CodeCodex
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 subagent.
Skill Claude CodeCodex
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, adding a…
Skill Claude CodeCodex
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.
Plugin Claude Code
Language-server intelligence (diagnostics, navigation) for Go, Rust, TypeScript, and Python. Opt-in companion to core — requires the language servers installed on PATH.
Plugin Claude Code
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.
MCP server Claude CodeCodexCursor +2
Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.
MCP server Claude CodeCodexCursor +2
Lets the agent fetch a URL and read its content as markdown. Runs locally from the mcp-server-fetch Python package.
MCP server Claude CodeCodexCursor +2
Lets the agent read, search and manipulate local git repositories: log, diff, status, commit. Runs locally from the mcp-server-git Python package.
Hook
Runs when a session starts, executing inject-context.sh and scan-untrusted-context.sh (2 commands). From dshakes/compass.
Hook
Runs when you submit a prompt, before the agent sees it, executing scan-prompt.sh. From dshakes/compass.
Hook
Runs before the agent uses a tool for Bash, Edit, Write, MultiEdit and NotebookEdit tool calls, executing protect-paths.sh and budget-gate.sh (2 commands). From dshakes/compass.
Hook
Runs after a tool call finishes for Edit, Write, MultiEdit, WebFetch, WebSearch and Bash tool calls, executing format-on-edit.sh and scan-tool-output.sh (2 commands). From dshakes/compass.
Hook
Runs when the agent finishes a response, executing notify.sh. From dshakes/compass.