AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
mapuamap avatar

mapuamap

8 listings · 0 installs

Open-source publisher. Listings imported from github.com/mapuamap — credited to the original author with their license.

↗ github.com/mapuamap
8 results
Self-run
SKILL

M Code Refactor

Refactor or restructure code safely in small, behavior-checked slices. Two behavior modes — preserve (legacy modernization, no behavior change) or may-change (architecture improvement) — each runnable as report-only or as a patch. Establishes a baseline and a test safety net before moving code, introduces seams before extraction, and justifies every new abstraction by concrete friction. Use for l…

0
2
Free
Self-run
SKILL

M Go

Resume the last saved work session — read the standing handoff file `.m_last_task.md` (written by /m_save) at the project root, restore context by reading the key files it names, then continue from its recorded "next step". Use at the start of a fresh session to pick up exactly where the previous one stopped.

0
4
Free
Self-run
SKILL

M Code Init Project

Initialize or harden a project for AI-assisted development — CLAUDE.md, .claude/rules, architecture boundaries, seams for nondeterminism, deterministic check commands, first behavior tests, and CI readiness. Use when bootstrapping a new repo or making an existing one safe for repeated Claude-assisted change.

0
3
Free
Self-run
SKILL

M Plan Roll

Autonomous "full send" of the m_plan pipeline — plan at large scope and implement, no questions. Forces the full 9-artifact plan, decides every blocker itself (recording assumptions), then chains straight into m_plan_implement and drives to done + deploy + verify without pausing. Use when you explicitly want the whole architect → build → deploy → verify cycle run hands-off on a substantial task.…

0
2
Free
Self-run
SKILL

M Plan Implement

Execute and verify a plan previously generated by /m_plan, including deployment to the real declared environment rather than treating local checks as release proof. Loads existing artifacts from .m_plan/<task-slug>/, walks 05_step_plan.md, enforces 06_deploy_plan.md real-target deploy/smoke gates, updates 09_verification.md, then reports Done / Changed / Not done. /goal mode is opt-in. Use when u…

0
2
Free
Self-run
SKILL

M Save

Snapshot the current work into the standing handoff file `.m_last_task.md` at the project root — task, what's done, what's in progress, next step, key files, decisions, blockers, and the commands to build/test. Overwrites the previous snapshot (one standing file, not a log). Use before ending a session, switching tasks, or when context is getting long, so /m_go can resume later.

0
4
Free
Self-run
SKILL

M Code Rules Audit

Audit code against the rules that actually exist in this repo (CLAUDE.md, .claude/rules, configs, CI) plus the deterministic checks that can run safely — architecture boundaries, tests, typecheck, lint, build, security-sensitive changes. report-only by default. Use for PR/commit readiness and rule-compliance checks; complements /code-review, which is rule-agnostic.

0
3
Free
Self-run
SKILL

M Plan

Plan + Execute + Verify pipeline for a user-supplied task. Asks blocker/architectural questions upfront via AskUserQuestion and probes deploy/e2e readiness (real target, access, secrets, browser tooling) before generating artifacts so those blockers surface at plan time, not deploy time, right-sizes the artifact set (4–9 docs depending on task class — tiny/small/medium/large), generates plans und…

0
7
Free
You've reached the end · 8 loaded