Skip to content

Credits ​

Muster's design was inspired by atomic-claude (site), superpowers, and gsd-core. It vendors a curated set of MIT-licensed skills and agents, and every skill, agent, command, output style and pipeline that is based on an external repository or work (an article, book, paper, standard, talk or person) says which one in its own upstream: field.

How provenance is recorded ​

vendor/manifest.yaml is the single source of truth. Each item's upstream: field, the catalog provenance summary, and NOTICE (with each upstream's copyright line) are generated from it by muster provenance --write, and the test suite fails when any of them drift. An item with upstream: [] is Muster-authored. A repository entry names the repository, the pinned commit, the upstream path, the license, and the relation; a work entry names its kind, title, author and link. An origin Muster's history mentions but never names is recorded as unknown with a dated note saying what was searched. Relations:

RelationMeaning
vendoredupstream text carried essentially unchanged
adaptedupstream text edited
mechanism-porta mechanism re-implemented in new text
inspired-byan idea, structure, or framework named; no text carried over

A work is always inspired-by: Muster takes ideas, frameworks or structure from it, never its text.

The Codex plugin carries the same record as NOTICE and PROVENANCE.md, since Codex skill headers cannot hold the field.

Vendored sources ​

SourceLicenseProvides
obra/superpowersMITBrainstorming, planning, TDD, code-review, debugging, verification skills
wshobson/agentsMITSoftware and knowledge-work agents and skills across many specialties
open-gsd/gsd-coreMITPlan, execute, and verify workflow phases (and the Codex muster-gsd-* fallbacks)

Other sources ​

Every non-vendored source, generated from the manifest. Each row lists the items it is the basis for.

Repositories ​

SourceLicenseBasis forRelation
pbakaus/impeccable @ b856e5010f2dApache-2.026 vendored builtins and agentsinspired-by, adapted
obra/superpowers @ 22f0b463e7a5MIT31 vendored builtins and agentsadapted, vendored
wshobson/agents @ 9c61ab243defMIT98 vendored builtins and agentsadapted, vendored
anthropics/skills @ 2c5958ecac7cApache-2.04 vendored builtins and agentsadapted, vendored
Leonxlnx/taste-skill-classics @ 5e08c9383dc4MIT4 vendored builtins and agentsvendored
addyosmani/agent-skills @ 301b02b12bffMIT3 vendored builtins and agentsadapted, vendored
emilkowalski/skills @ 715c1807e08cMIT23 vendored builtins and agentsvendored
nutlope/hallmark @ 7e213cb6feb4MIT109 vendored builtins and agentsadapted, vendored
greensock/gsap-skills @ aed9cfd32777MIT8 vendored builtins and agentsvendored
elayadesign/ai-design-skills @ 456d9e0d3e2dMIT2 vendored builtins and agentsvendored
jakubkrehel/skills @ 8b254eb75dadMIT46 vendored builtins and agentsvendored
gotalab/cc-sdd @ e2a0c671aef3MIT2 vendored builtins and agentsvendored
K-Dense-AI/scientific-agent-skills @ 2d2065fb4520MIT36 vendored builtins and agentsvendored, adapted
AminBlg/SimpleEnglish @ 300432a9e4c4MIT5 vendored builtins and agentsvendored
supabase/agent-skills @ c9be0e931b79MIT33 vendored builtins and agentsvendored
samber/cc-skills-golang @ d68d80aec298MIT28 vendored builtins and agentsvendored
Nanako0129/sepia @ 0eb11d6c64c9MIT20 vendored builtins and agentsvendored
haowjy/creative-writing-skills @ 15003a6fd5a1Apache-2.031 vendored builtins and agentsvendored
haowjy/creative-writing-skills @ 15003a6fd5a1Apache-2.0book-developmental-editor, book-line-editor, book-continuity-checker, book-beta-readerinspired-by
danjdewhurst/story-skills @ 3c0e0346ee09MITbook-continuity-checker, book-beta-reader, book-runinspired-by
Calliope-Editor/writing-skills @ 2fad031982cbMITbook-continuity-checker, book-runinspired-by
epicsagas/Velith @ 5ddd29675c5fApache-2.0book-beta-reader, book-runinspired-by
clutcher/book-writing-skills @ 0bea387d1fe1MITbook-runinspired-by
PenglongHuang/chinese-novelist-skill @ 507d41567925MITbook-writerinspired-by
howells/fiction @ 2f256acbfce6NONEbook-continuity-checkerinspired-by
felipelobomotta-blip/book-genesis-studio @ 88e2e0047ad2MITbook-beta-readerinspired-by
open-gsd/gsd-core @ 9385f4618b52MIT42 vendored builtins and agentsadapted, vendored
nextlevelbuilder/ui-ux-pro-max-skill @ 4f2dbb67e649MIT144 vendored builtins and agentsvendored, inspired-by, adapted
ghaida/intent @ 1806110106a4CC0-1.044 vendored builtins and agentsvendored, inspired-by, adapted
bergside/typeui @ efc5f21dff38MIT4 vendored builtins and agentsadapted
skovalik/perception-first-design @ 1704ff61c188CC-BY-SA-4.040 vendored builtins and agentsvendored, adapted
ai-evals-course/evals-skills @ 80d5f7b0127cApache-2.07 vendored builtins and agentsvendored, inspired-by, adapted
getsentry/skills @ e94f22214528Apache-2.012 vendored builtins and agentsvendored, inspired-by, adapted
getsentry/skills @ e94f22214528CC-BY-SA-4.023 vendored builtins and agentsinspired-by, adapted, vendored
openai/skills @ 49f948faa925Apache-2.05 vendored builtins and agentsinspired-by, adapted, vendored
trailofbits/skills @ e4dd0bb5b155CC-BY-SA-4.026 vendored builtins and agentsvendored, inspired-by, adapted
anthropics/claude-plugins-official @ dceb15d50832Apache-2.04 vendored builtins and agentsvendored, adapted
mattpocock/skills @ 4ae2317ddb22MIT15 vendored builtins and agentsvendored, inspired-by, adapted
obra/superpowers-lab @ 51111f74f240MIT8 vendored builtins and agentsvendored, inspired-by, adapted
addyosmani/agent-skills @ 301b02b12bffMIT1 vendored builtins and agentsadapted
open-gsd/gsd-core @ 1c352d1ea37bMITmuster-gsd-plan-phase, muster-gsd-execute-phase, muster-gsd-verify-workmechanism-port
wshobson/agents @ 2de74ac1c8f6MITwsh-signed-audit-trails-recipe, wsh-code-reviewermechanism-port, vendored
blader/humanizer @ b48c832f0f80MITmuster-humanizeradapted
rudra496/StealthHumanizer @ 8b0e90874c61MITmuster-humanizeradapted
conorbronsdon/avoid-ai-writing @ 30971f1c50c6MITmuster-humanizeradapted
jalaalrd/anti-ai-slop-writing @ 63255f9bbb75NONEmuster-humanizerinspired-by
aaaronmiller/humanize-writing @ c07a2a8dab1fMITmuster-humanizeradapted
linexjlin/GPTs @ 3adfb7b38423NONEmuster-humanizerinspired-by
hardikpandya/stop-slop @ 8da1f030185bMITmuster-humanizeradapted
petergyang/no-ai-slop @ 000650b15698MITmuster-humanizeradapted
hermes-labs-ai/lintlang @ 645f57879ff5Apache-2.0muster-prompt-smithmechanism-port
promptfoo/promptfoo @ 8569e72ed6cfMITmuster-prompt-smithinspired-by
shobrook/promptimal @ e03cbc1db19cMITmuster-prompt-smithinspired-by
gepa-ai/gepa @ ce5b0d6e3d6aMITmuster-prompt-smithinspired-by
felipelobomotta-blip/book-genesis-studio @ c2fc628fd5d1MITbook, muster-scorermechanism-port, inspired-by
NousResearch/autonovel @ d165f267a0ffNONEbook, book-runinspired-by
CSHaitao/Awesome-LLMs-as-Judges @ d89ed4241b81NONEmuster-scorerinspired-by
llm-as-a-judge/Awesome-LLM-as-a-judge @ ad3b4ce1d869NONEmuster-scorerinspired-by
microsoft/LLM-Rubric @ 030ab161e5afMITmuster-scorerinspired-by
assafelovic/gpt-researcher @ 597a99e2ef87Apache-2.0muster-researchinspired-by
mbzuai-nlp/qraft @ 3bbea66c832dNONEmuster-researchinspired-by
damusix/atomic-claude @ b4ca195cae60MITmuster-surgeon, muster-reviewer, muster-investigator, muster-strategist, muster-improver, improve, musterinspired-by
obra/superpowers @ d884ae04edebMITmuster-runnermechanism-port
wshobson/agents @ 511f8345cf42MITmuster-runnermechanism-port
VoltAgent/awesome-claude-code-subagents @ 14bbcf5d984cMITmuster-runnermechanism-port
humanlayer/12-factor-agents @ d20c728368bfApache-2.0 AND CC-BY-SA-4.0muster-runnermechanism-port
contains-studio/agents @ a5a480c324caNONEmuster-runnerinspired-by
disler/infinite-agentic-loop @ 6e9a012f81efNONEmuster-runnerinspired-by
hesreallyhim/awesome-claude-code @ 957922fca4ccCC-BY-NC-ND-4.0muster-runnerinspired-by
deanpeters/product-manager-prompts @ 418049a64858CC-BY-NC-SA-4.0prd, epicinspired-by
deanpeters/Product-Manager-Skills @ 70fb6c4e4163CC-BY-NC-SA-4.0prd, epic, launch-planinspired-by
phuryn/pm-skills @ 9af7bfd0bc47MIT8 vendored builtins and agentsinspired-by, adapted
github/spec-kit @ 08252af8c5fbMITmuster-pminspired-by
Fission-AI/OpenSpec @ 579fcac57ae0MITmuster-pminspired-by
Wirasm/prp @ 435292597e7bMITmuster-pminspired-by
product-on-purpose/pm-skills @ 9b920db418c5Apache-2.06 vendored builtins and agentsinspired-by, adapted
phuryn/product-engineering @ 061014ffe954MIT3 vendored builtins and agentsadapted
open-gsd/gsd-core @ 9385f4618b52MITmuster-pminspired-by
anthropics/knowledge-work-plugins @ e605d8ddbfb6Apache-2.06 vendored builtins and agentsinspired-by, adapted
joelparkerhenderson/objectives-and-key-results @ f7269521672aNONEokrsinspired-by
architecture-decision-record/architecture-decision-record @ a36c53f49517CC-BY-NC-SA-4.0designinspired-by
adr/madr @ ba75bb1b20d4MIT OR CC0-1.0designinspired-by
olivierlacan/keep-a-changelog @ 08d0df5a7e93MITrelease-notesinspired-by
gcamilo/management-consulting @ dd2d099dc390MITexecutive-summaryinspired-by
reasoncommons/issuetrees @ 56ad78e0ce78NONEexecutive-summaryinspired-by
cdeust/ai-prd-generator @ 4189d41b102dLicenseRef-proprietaryprdinspired-by
coreyhaines31/marketingskills @ 8a3bde8083bdMIT8 vendored builtins and agentsinspired-by
CosmoBlk/email-marketing-bible @ 962648c1b147MITcompetitive-battlecard, lead-magnet, case-study, newsletterinspired-by
AgriciDaniel/claude-email @ 182270a0bbcdMITcompetitive-battlecard, lead-magnet, case-study, newsletterinspired-by
SkeltonThatcher/run-book-template @ 7014714b6021NONErunbookinspired-by
dastergon/awesome-sre @ e91ef69aa521CC0-1.0runbookinspired-by
runbear-io/awesome-runbook @ d83a294e4eb6CC0-1.0runbookinspired-by
Scoutflo/Scoutflo-SRE-Playbooks @ acc55da0224fMITrunbookinspired-by
WynterJones/CoppieGPT @ 96fc78149f03NONEmuster-authorinspired-by
boraoztunc/skills @ 1209fb6b07b8Apache-2.0muster-authorinspired-by

Works ​

Articles, books, papers, standards, talks and people whose ideas, frameworks or structure an item is based on. No text is carried from them.

WorkKindBasis for
How to Write a Novel Using the Snowflake Method, Randy Ingermansonbookbook-run
Unlock AI: Open Engine and Open Skills, Nate B. Jonespersonreview-gate, muster-humanizer, muster-image, muster-research, prd, case-study, newsletter, blog-post, social-post
Building effective agents, Erik Schluntz and Barry Zhang (Anthropic)articlemuster-runner
Create custom subagents (Claude Code docs), Anthropicarticlemuster-runner
LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion, Dongfu Jiang, Xiang Ren and Bill Yuchen Lin (ACL 2023)papertournament
Prompting best practices (Claude Docs), Anthropicarticlemuster-prompt-smith
Reduce hallucinations (Claude Docs, Strengthen guardrails), Anthropicarticlemuster-prompt-smith
Define success criteria and build evaluations (Claude Docs), Anthropicarticlemuster-prompt-smith, muster-pm
Demystifying evals for AI agents, Anthropicarticlemuster-pm
Evaluation best practices (OpenAI API docs), OpenAIarticlemuster-pm
Your AI Product Needs Evals, Hamel Husainarticlemuster-pm
AI Evals: Everything You Need to Know, Hamel Husain and Shreya Shankararticlemuster-pm
The new rules of context engineering for Claude 5 generation models, Anthropicarticlemuster-prompt-smith
LLM-Citepapermuster-research
Wikipedia:Signs of AI writing, WikiProject AI Cleanup (Wikipedia editors)articlemuster-humanizer
AIDA (Attention, Interest, Desire, Action), E. St. Elmo Lewispersonmuster-author, social-post, lead-magnet
The QUEST copywriting formula, Michel Fortinarticlemuster-author, social-post
How to Write Copy That Sells (the PASTOR framework), Ray Edwardsbookmuster-author
Breakthrough Advertising (awareness and sophistication), Eugene M. Schwartzbookmuster-author
Search Quality Rater Guidelines (E-E-A-T), Googlestandardmuster-author, blog-post
Creating helpful, reliable, people-first content, Google Search Centralarticleblog-post
GEO: Generative Engine Optimization, Pranjal Aggarwal et al. (KDD 2024)paperblog-post
AICMO marketing prompt collection; MaxsPromptsarticlecompetitive-battlecard, lead-magnet, case-study, newsletter
Sales Battlecards 101, Kluearticlecompetitive-battlecard
Modern battlecard blueprint, Crayonarticlecompetitive-battlecard
Challenge-Solution-Results case study structure, libril.com and geisheker.comarticlecase-study
Email deliverability guidance, Litmus and Validityarticlenewsletter
The Hero with a Thousand Faces, Joseph Campbellbookcase-study
Building a StoryBrand (SB7), Donald Millerbookbook, case-study
The Pyramid Principle (SCQA, MECE), Barbara Mintobookexecutive-summary, book
Save the Cat!, Blake Snyderbookbook, book-run
The Story Grid, Shawn Coynebookbook, book-run
Techniques of the Selling Writer (scene and sequel), Dwight V. Swainbookbook, book-run
Chapter Blog nonfiction outline; ProWritingAid non-fiction structurearticlebook, book-run
Competing Against Luck (Jobs to Be Done), Clayton M. Christensen, Taddy Hall, Karen Dillon and David S. Duncanbookmuster-author, prd, epic
Lean UX (hypothesis statements, proto-personas), Jeff Gothelf and Josh Seidenbookprd, epic
The Humanizing Work Guide to Splitting User Stories, Richard Lawrence and Peter Greenarticleepic
User Story Mapping, Jeff Pattonbookepic
Working Backwards (PR/FAQ), Colin Bryar and Bill Carrbooklaunch-plan
Semantic Versioning 2.0.0, Tom Preston-Wernerstandardrelease-notes
Measure What Matters (OKRs), John Doerrbookokrs
High Output Management, Andrew S. Grovebookokrs
RICE: simple prioritization for product managers, Sean McBride (Intercom)articleroadmap, muster-roadmap
The Now-Next-Later roadmap, Janna Bastow (ProdPad)articleroadmap, muster-roadmap
Documenting Architecture Decisions, Michael Nygardarticledesign
ISO/IEC/IEEE 29119-3, Software testing: Test documentation, ISO/IEC/IEEEstandardai-test-plan
IEEE 829, Standard for Software and System Test Documentation (withdrawn), IEEEstandardai-test-plan
Site Reliability Engineering (Managing Incidents), Betsy Beyer, Chris Jones, Jennifer Petoff and Niall Richard Murphy (Google)bookrunbook
PagerDuty Incident Response documentation, PagerDutyarticlerunbook
Runbook practice articles (preconditions, observability, escalation, cleanup, idempotency), emmer.dev, The Good Shell and Rootlyarticlerunbook
10 Usability Heuristics for User Interface Design, Jakob Nielsen (Nielsen Norman Group)articleaudit-pattern-design-ux
Timeless documentation (Google developer documentation style guide), Googlearticleaudit-pattern-documentation
Diátaxis, Daniele Procidaarticleaudit-pattern-documentation
Cognitive Complexity, Because Testability != Understandability, G. Ann Campbell (SonarSource)articleaudit-pattern-readability
OWASP Top 10:2021 A08, Software and Data Integrity Failures, OWASP Foundationstandardaudit-pattern-security

Origins not yet identified ​

Muster's history says these items drew on sources it never named. Each note records what was searched.

WhatNoteBasis for
PAS (Problem-Agitate-Solution) and BAB (Before-After-Bridge) copywriting formulas2026-11-09: named in muster-author, social-post, lead-magnet and book. Neither muster's history nor a primary source found on this date names who originated either formula.muster-author, social-post, lead-magnet, book
The "high-signal sources" behind the first content rubrics2026-11-09: commit b99599a (2026-06-07) says the blog, social, lead-magnet, newsletter, case-study and runbook rubrics were "grounded in AIDA/PAS/BAB/QUEST + E-E-A-T from high-signal sources" without naming them; no doc was committed with it. The 2026-06-08 research note (b122ed9) names later sources for most of these pipelines, recorded here as their own entries; the original set is not recoverable.blog-post, social-post, lead-magnet, newsletter, case-study, runbook
BLUF (bottom line up front)2026-11-09: named in executive-summary. A military-correspondence convention; no single originating work was identified on this date.executive-summary

License review ​

Some sources carry no license, a NonCommercial or NoDerivatives license, or a proprietary one, so Muster has no right to reuse their text. Each was compared with the Muster items based on it, and the manifest records the result as a licenseReview: ideas-only when no text was carried, or clean-room-rewrite when Muster text that followed the source too closely was rewritten from the underlying idea (on 2026-11-09: the humanizer's vocabulary lists, the PRD section structure, the epic hypothesis template, and five quotations in the audit hunt lists, now paraphrased with their links kept). The test suite fails on any such source without a review, and on any waiver still pending a decision.

Upstream routing on Codex ​

On Codex, Muster prefers an enabled authoritative upstream implementation over its own copy whenever one exists: the official Superpowers plugin, wshobson's per-plugin Codex skills, and GSD's installer-generated Codex skills.

The bundled sp-*, wsh-*, and muster-gsd-* skills are deterministic fallbacks: they keep every role resolvable when an upstream is absent, and they never implicitly install those providers on your behalf. The pinned compatibility survey — which upstreams were checked, at which refs, including Atomic Codex, Book Genesis, the humanizer sources, and Promptfoo — is recorded in codex/upstreams.json.

Clean-room specialists ​

Alongside the vendored material, Muster ships its own specialists in plugin/agents/, authored fresh from atomic-claude's role concept:

  • muster-surgeon: precise 1-2 file edits
  • muster-investigator: read-only locator
  • muster-strategist: heavyweight reasoning
  • muster-improver: read-only post-run retrospective that proposes self-improvement edits

The muster-runner agent (built from the lifecycle mechanisms credited above) left the Claude plugin in revival stage 2b. It survives only as the frozen Codex lane's production-wave policy, in codex/frozen/agents/muster-runner.md.

Lifecycle seats adapted from GSD ​

The stage-2 lifecycle agents are adapted from gsd-core v1.20.1 agents (MIT). gsd's measured protocol text (honest abstain, the evidence gate, revision-loop limits, failing direction, the must-NOT probe, deviation rules, the self-check and the destructive-git ban) is carried verbatim in marked regions; muster vendor update gsd keeps them in sync by 3-way merge:

  • muster-planner: writes the run's PLAN.md (from gsd-planner)
  • muster-plan-checker: checks PLAN.md before execution (from gsd-plan-checker)
  • muster-executor: implements one task in its own worktree (from gsd-executor, with the former builder's one-slice scope contract)
  • muster-verifier: goal-backward verification with honest abstain (from gsd-verifier)
  • muster-reviewer: adversarial review of one task's commits (from gsd-code-reviewer, with muster's verdict discipline)
  • muster-test-writer: writes a task's failing tests before anyone implements it (from gsd-nyquist-auditor)
  • muster-integration-checker: checks that a wave's parallel tasks wire together (from gsd-integration-checker)

The muster:debug workflow's hypothesis investigator, wsh-team-debugger, is adapted from wshobson's agent-teams team-debugger (MIT).

Additional inspiration (clean-room, mechanism-level) ​

A cluster of systems introduced in 0.5.0 -- the sprint coordination protocol (claim/receipt/ledger discipline), the citation-guard gate, QA runbook memory, the voice/audience/brand profile system, newsletter signal-diff, the assumption checker, and the document-ingestion contract -- were designed with mechanism-level inspiration from Nate B. Jones's Unlock AI open-skills/open-engine patterns (unlock-ai.natebjones.com). No code, prose, or configuration was copied; Muster's implementations are original, adapted to its own deterministic-CLI/model-facing-skill architecture. The Unlock AI library is members-only, so this could not be checked against its text; the items it informed are listed under Works above.

License ​

Muster is licensed under Apache-2.0. See LICENSE and NOTICE.

Contributing ​

Contributions are welcome. See CONTRIBUTING.md to get started.

Released under the Apache-2.0 License.