vahaah/astack
One plugin that gives coding agents a full working method: planning, test-first slices, review, hardening and safe merges. Builds for Claude Code, Codex, Cursor, Grok Build and Agent Skills clients. Adapts pstack, Matt Pocock's skills and t
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/vahaah/astack MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit <redacted> .claude/skills/architect $ npx degit <redacted> .claude/skills/arena $ npx degit <redacted>-checklist .claude/skills/benchmark-checklist $ npx degit <redacted>-radius .claude/skills/blast-radius $ npx degit <redacted>-review .claude/skills/code-review $ npx degit <redacted>-design .claude/skills/codebase-design $ npx degit <redacted>-guide .claude/skills/coding-guide $ npx degit <redacted>-rules .claude/skills/coding-rules $ npx degit <redacted>-cli .claude/skills/control-cli $ npx degit <redacted>-ui .claude/skills/control-ui $ npx degit <redacted> .claude/skills/correct $ npx degit <redacted>-verification-skill .claude/skills/create-verification-skill $ npx degit <redacted> .claude/skills/deslop $ npx degit <redacted>-bugs .claude/skills/diagnosing-bugs $ npx degit <redacted>-modeling .claude/skills/domain-modeling $ npx degit <redacted>-it-out .claude/skills/figure-it-out $ npx degit <redacted> .claude/skills/grilling $ npx degit <redacted> .claude/skills/how $ npx degit <redacted>-spec .claude/skills/implement-spec $ npx degit <redacted> .claude/skills/implement $ npx degit <redacted>-codebase-architecture .claude/skills/improve-codebase-architecture $ npx degit <redacted>-your-own-words .claude/skills/in-your-own-words $ npx degit <redacted> .claude/skills/interrogate $ npx degit <redacted>-verification-skill .claude/skills/maintain-verification-skill $ npx degit <redacted> .claude/skills/mode $ npx degit <redacted>-comments .claude/skills/no-comments $ npx degit <redacted> .claude/skills/plan $ npx degit <redacted>-review-hardening .claude/skills/pr-review-hardening $ npx degit <redacted> .claude/skills/principles $ npx degit <redacted> .claude/skills/prototype $ npx degit <redacted> .claude/skills/recall $ npx degit <redacted> .claude/skills/reflect $ npx degit <redacted> .claude/skills/research $ npx degit <redacted> .claude/skills/retro $ npx degit <redacted>-models .claude/skills/setup-models $ npx degit <redacted> .claude/skills/setup $ npx degit <redacted> .claude/skills/sharpen $ npx degit <redacted>-me-your-work .claude/skills/show-me-your-work $ npx degit <redacted> .claude/skills/swarm $ npx degit <redacted> .claude/skills/tdd
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (90)
architectarenabenchmark-checklistblast-radiuscode-reviewcodebase-designcoding-guidecoding-rulescontrol-clicontrol-uicorrectcreate-verification-skilldeslopdiagnosing-bugsdomain-modelingfigure-it-outgrillinghowimplement-specimplementimprove-codebase-architecturein-your-own-wordsinterrogatemaintain-verification-skillmodeno-commentsplanpr-review-hardeningprinciplesprototyperecallreflectresearchretrosetup-modelssetupsharpenshow-me-your-workswarmtddto-questionnaireto-specto-ticketstriagetypeswait-whatwayfinderwhywizardwrite-docswrite-ticketwriting-for-agentsreproduce-and-fix-issuessetup-bennytriage-issue-reportsautomate-mebroketchupMake Bot UIpoteto-helpPoteto Modeprinciple-attack-the-premiseprinciple-boundary-disciplineprinciple-build-the-leverprinciple-encode-lessons-in-structureprinciple-exhaust-the-design-spaceprinciple-experience-firstprinciple-explain-the-numberprinciple-fix-root-causesprinciple-foundational-thinkingprinciple-guard-the-context-windowprinciple-laziness-protocolprinciple-make-operations-idempotentprinciple-migrate-callers-then-delete-legacy-apisprinciple-minimize-reader-loadprinciple-model-the-domainprinciple-never-block-on-the-humanprinciple-outcome-oriented-executionprinciple-prove-it-worksprinciple-redesign-from-first-principlesprinciple-separate-before-serializing-shared-stateprinciple-sequence-verifiable-unitsprinciple-subtract-before-you-addprinciple-test-behavior-not-implementationprinciple-type-system-disciplinesetup-pstackteachtechnical-writingtypescript-best-practicesunslop
Similar rigs
ystory/pstack-for-codex
Unofficial Codex adaptation of pstack workflows, skills, and agents, with native Codex and Claude Code execution.
Skill Collector 4.1k tok · · Q0
janrizmlibres/claude-pstack
pstack for Claude Code: a port of Lauren Tan's Cursor plugin of agent workflows, kept in step with upstream. Runs locally and in cloud sessions.
Skill Collector 4.0k tok · · Q0
ystory/pstack
Unofficial Codex adaptation of pstack workflows, skills, and agents, with native Codex and Claude Code execution.
Skill Collector 4.6k tok · · Q0
janrizmlibres/claude-jrzstack
pstack for Claude Code: a port of Lauren Tan's Cursor plugin of agent workflows, kept in step with upstream. Runs locally and in cloud sessions.
Skill Collector 4.2k tok · · Q0