principles
Skill41k starsChanged 5 days agoMITView on GitHub
Twenty-four engineering principles in five groups, mapped to the lane carrying each — premise testing, root causes, honest verification, domain modeling, convergence, context discipline. For design, debugging, or delegation briefs.
16 other projects use a version of this, 4 of them edited.
Trending
More talk lately.about the whole repository
Most recently taken up by
- Yeachan-Heo/oh-my-claude-sisyphusword for word, first seen Nov 8, 2026
- scottlivingston/claude-skillstheir own version, first seen Nov 8, 2026
- endqwerty/endstackedited, first seen Nov 8, 2026
- Belweave/hstacktheir own version, first seen Nov 8, 2026
- Pixxle/skillsedited, first seen Nov 1, 2026
- christofferbergj/agent-skillstheir own version, first seen Nov 1, 2026
Who's talking about Yeachan-Heo/oh-my-claudecode
- Prism Labs“Oh My Claude Code: Multi-Agent Orchestration with Zero Learning Curve”YouTube · Mar 25, 2026 · 6.6k views
- Ultrathink Engineer by Sigrid Jin“Interview with Bellman: The Harness Engineer of oh-my-codex and oh-my-claudecode”YouTube · Mar 5, 2026 · 4k views
- Prism Labs“32 Agents, 6 Modes, Zero Learning Curve 🤖 Oh My Claude Code #Shorts”YouTube · Mar 25, 2026 · 3.6k views
- Gourcer“Yeachan-Heo/oh-my-claudecode - Gource visualisation”YouTube · Mar 27, 2026 · 2.8k views
- Repocast | GitHub 일일 브리핑“클로드 코딩 전문가 되기? oh-my-claudecode가 답이다!”YouTube · Mar 26, 2026 · 1.3k views
The biggest 5 of 84 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 84
Talked about on GitHub, YouTube, Bluesky and the web (84 times).
On GitHub · 50
- May 4, 2026Upgrade skill frontmatter for declarative composition (pipelines, handoffs, model hints) — TechNickAI/ai-coding-config2 reactions · 2 comments
- May 4, 2026Add verify-deliverables SubagentStop hook to harden subagent completion claims — TechNickAI/ai-coding-config2 reactions · 2 comments
- May 5, 2026[redesign-research] oh-my-claudecode first-pass survey (cycle 75 dispatch — companion to oh-my-codex per #2774) — EvaLok/schema-org-json-ld1 reaction · 3 comments
- Mar 8, 2026feat: Add OMC (oh-my-claudecode) and OMX (oh-my-codex) agent runners — junhoyeo/contrabass1 reaction · 1 comment
- Feb 6, 2026fix(ai-dev): use Claude Code plugin system for oh-my-claudecode — danstis/coder-templates1 reaction
45 more on GitHub
- Nov 4, 2026Review and adopt oh-my-claudecode patterns — cbartens/bkit0 reactions
- Nov 3, 2026claude-code-marketplaces.github.yeachan-heo.oh-my-claudecode: 5.7.30 → 5.7.31 — sudosubin/agents.nix0 reactions
- Nov 3, 2026claude-code-plugins.github.yeachan-heo.oh-my-claudecode: 5.7.30 → 5.7.31 — sudosubin/agents.nix0 reactions
- Nov 3, 2026agent-skills.github.yeachan-heo.oh-my-claudecode: 5.7.30 → 5.7.31 — sudosubin/agents.nix0 reactions
- Nov 2, 2026agent-skills.github.yeachan-heo.oh-my-claudecode: 5.7.29 → 5.7.30 — sudosubin/agents.nix0 reactions
- Nov 2, 2026claude-code-marketplaces.github.yeachan-heo.oh-my-claudecode: 5.7.29 → 5.7.30 — sudosubin/agents.nix0 reactions
- Nov 2, 2026claude-code-plugins.github.yeachan-heo.oh-my-claudecode: 5.7.29 → 5.7.30 — sudosubin/agents.nix0 reactions
- Nov 1, 2026claude-code-plugins.github.yeachan-heo.oh-my-claudecode: 5.7.26 → 5.7.29 — sudosubin/agents.nix0 reactions
- Nov 1, 2026claude-code-marketplaces.github.yeachan-heo.oh-my-claudecode: 5.7.27 → 5.7.29 — sudosubin/agents.nix0 reactions
- Nov 1, 2026claude-code-marketplaces.github.yeachan-heo.oh-my-claudecode: 5.7.26 → 5.7.27 — sudosubin/agents.nix0 reactions
- Nov 1, 2026agent-skills.github.yeachan-heo.oh-my-claudecode: 5.7.25 → 5.7.29 — sudosubin/agents.nix0 reactions
- Nov 1, 2026claude-code-marketplaces.github.yeachan-heo.oh-my-claudecode: 5.7.25 → 5.7.26 — sudosubin/agents.nix0 reactions
- Nov 1, 2026claude-code-plugins.github.yeachan-heo.oh-my-claudecode: 5.7.25 → 5.7.26 — sudosubin/agents.nix0 reactions
- Nov 1, 2026agent-skills.github.yeachan-heo.oh-my-claudecode: 5.7.24 → 5.7.25 — sudosubin/agents.nix0 reactions
- Nov 1, 2026claude-code-marketplaces.github.yeachan-heo.oh-my-claudecode: 5.7.24 → 5.7.25 — sudosubin/agents.nix0 reactions
- Nov 1, 2026claude-code-plugins.github.yeachan-heo.oh-my-claudecode: 5.7.24 → 5.7.25 — sudosubin/agents.nix0 reactions
- Nov 1, 2026agent-skills.github.yeachan-heo.oh-my-claudecode: 5.7.23 → 5.7.24 — sudosubin/agents.nix0 reactions
- Oct 31, 2026claude-code-marketplaces.github.yeachan-heo.oh-my-claudecode: 5.7.23 → 5.7.24 — sudosubin/agents.nix0 reactions
- Oct 31, 2026claude-code-plugins.github.yeachan-heo.oh-my-claudecode: 5.7.23 → 5.7.24 — sudosubin/agents.nix0 reactions
- Oct 31, 2026claude-code-marketplaces.github.yeachan-heo.oh-my-claudecode: 5.7.22 → 5.7.23 — sudosubin/agents.nix0 reactions
- Oct 31, 2026claude-code-plugins.github.yeachan-heo.oh-my-claudecode: 5.7.22 → 5.7.23 — sudosubin/agents.nix0 reactions
- Oct 31, 2026agent-skills.github.yeachan-heo.oh-my-claudecode: 5.7.22 → 5.7.23 — sudosubin/agents.nix0 reactions
- Oct 30, 2026claude-code-plugins.github.yeachan-heo.oh-my-claudecode: 5.7.21 → 5.7.22 — sudosubin/agents.nix0 reactions
- Oct 30, 2026agent-skills.github.yeachan-heo.oh-my-claudecode: 5.7.21 → 5.7.22 — sudosubin/agents.nix0 reactions
- Oct 30, 2026claude-code-marketplaces.github.yeachan-heo.oh-my-claudecode: 5.7.21 → 5.7.22 — sudosubin/agents.nix0 reactions
- Oct 30, 2026agent-skills.github.yeachan-heo.oh-my-claudecode: 5.7.20 → 5.7.21 — sudosubin/agents.nix0 reactions
- Oct 30, 2026claude-code-marketplaces.github.yeachan-heo.oh-my-claudecode: 5.7.20 → 5.7.21 — sudosubin/agents.nix0 reactions
- Oct 30, 2026claude-code-plugins.github.yeachan-heo.oh-my-claudecode: 5.7.20 → 5.7.21 — sudosubin/agents.nix0 reactions
- Oct 29, 2026claude-code-plugins.github.yeachan-heo.oh-my-claudecode: 5.7.19 → 5.7.20 — sudosubin/agents.nix0 reactions
- Oct 29, 2026claude-code-marketplaces.github.yeachan-heo.oh-my-claudecode: 5.7.19 → 5.7.20 — sudosubin/agents.nix0 reactions
- Oct 29, 2026agent-skills.github.yeachan-heo.oh-my-claudecode: 5.7.19 → 5.7.20 — sudosubin/agents.nix0 reactions
- Oct 27, 2026agent-skills.github.yeachan-heo.oh-my-claudecode: 5.7.18 → 5.7.19 — sudosubin/agents.nix0 reactions
- Oct 27, 2026claude-code-plugins.github.yeachan-heo.oh-my-claudecode: 5.7.18 → 5.7.19 — sudosubin/agents.nix0 reactions
- Oct 27, 2026claude-code-marketplaces.github.yeachan-heo.oh-my-claudecode: 5.7.18 → 5.7.19 — sudosubin/agents.nix0 reactions
- Oct 27, 2026agent-skills.github.yeachan-heo.oh-my-claudecode: 5.7.17 → 5.7.18 — sudosubin/agents.nix0 reactions
- Oct 27, 2026claude-code-plugins.github.yeachan-heo.oh-my-claudecode: 5.7.17 → 5.7.18 — sudosubin/agents.nix0 reactions
- Oct 27, 2026claude-code-marketplaces.github.yeachan-heo.oh-my-claudecode: 5.7.17 → 5.7.18 — sudosubin/agents.nix0 reactions
- Oct 26, 2026agent-skills.github.yeachan-heo.oh-my-claudecode: 5.7.16 → 5.7.17 — sudosubin/agents.nix0 reactions
- Oct 26, 2026claude-code-plugins.github.yeachan-heo.oh-my-claudecode: 5.7.16 → 5.7.17 — sudosubin/agents.nix0 reactions
- Oct 26, 2026claude-code-marketplaces.github.yeachan-heo.oh-my-claudecode: 5.7.16 → 5.7.17 — sudosubin/agents.nix0 reactions
- Oct 26, 2026agent-skills.github.yeachan-heo.oh-my-claudecode: 5.7.15 → 5.7.16 — sudosubin/agents.nix0 reactions
- Oct 16, 2026Telemetry for Claude Code marketplace plugin installs via plugin hooks — aws-solutions/konductor0 reactions
- Oct 14, 2026Server-side if-shell fails with invalid inherited stdin after send-keys C-c (3.4.0 / OMC shutdown) — psmux/psmux0 reactions · 1 comment
- Oct 4, 2026copycat: deletion-first cleanup stage in /etp — lucasmccomb/ccgm0 reactions
- Oct 4, 2026copycat: off/shadow/active rollout for autoheal and dreaming decisions — lucasmccomb/ccgm0 reactions
On YouTube · 20
- Mar 25, 2026Oh My Claude Code: Multi-Agent Orchestration with Zero Learning Curve — Prism Labs6.6k views · 1 comment
- Mar 5, 2026Interview with Bellman: The Harness Engineer of oh-my-codex and oh-my-claudecode — Ultrathink Engineer by Sigrid Jin4k views · 5 comments
- Mar 25, 202632 Agents, 6 Modes, Zero Learning Curve 🤖 Oh My Claude Code #Shorts — Prism Labs3.6k views
- Mar 27, 2026Yeachan-Heo/oh-my-claudecode - Gource visualisation — Gourcer2.8k views · 3 comments
- Mar 26, 2026클로드 코딩 전문가 되기? oh-my-claudecode가 답이다! — Repocast | GitHub 일일 브리핑1.3k views · 1 comment
15 more on YouTube
- May 4, 2026oh-my-claudecode: Multi-Agent Orchestration for Claude Code — VibeDev1.1k views
- Mar 27, 202613K+ Stars • Automation | oh-my-claudecode — Multi-agent Orchestration for Claude Code #shorts — Neural-Nexus939 views
- Mar 28, 2026코드가 마법처럼 변신하는 비결?! oh-my-claudecode #GitHubTrending — Chloe Park405 views
- Oct 16, 2026I Let 8 Claude Agents Build an API (133 Tests Passed) — WifiCoding275 views
- Sep 14, 2026Introducing Oh-My-Claudecode! — Dann Paker AI240 views
- Jul 2, 2026Oh My ClaudeCode: Turn One Request Into A Verified Agent Team — BACKFIRED X205 views · 1 comment
- May 21, 2026Orquestre times de IA com oh-my-claudecode — em Claude Code, Codex e Gemini #AI #Shorts — RepoShots196 views · 1 comment
- Nov 2, 2026oh-my-claudecode - Teams-first Multi-agent Orchestration for Claude Code — RepoBytes | Find It. Understand It. Build With It.95 views
- Oct 11, 2026أداة oh-my-claudecode: أتمتة كود كلاود بذكاء #Shorts — Manea Alblooshi72 views
- Jul 25, 2026TypeScript開発者向け|Claude Codeにチーム開発を追加するoh-my-claudecodeの使い方 — さつきのOSS研究室71 views · 1 comment
- May 27, 2026GitHub - Yeachan-Heo/oh-my-claudecode: Teams-first Multi-agent orchestration for Claude Code — GitHub Daily Trend AI Podcast35 views
- Mar 29, 2026Oh-My-ClaudeCode: 나만의 AI 개발팀 — Decoded AI35 views
- Oct 6, 2026💡 [Open Source Alternative to Paid Tools] oh-my-claudecode: The Free Tool Taking Over GitHub! #shor — githubrepo_cloud25 views
- Aug 13, 2026빌드팀 추천 GitHub 리포 EP.97 — oh-my-claudecode — 세균무기 germweapon7 views
- Nov 4, 2026Coding Agent CLI · 5-5 플러그인: oh-my-claudecode와 oh-my-codex, 에이전트는 그대로 일하는 방식을 설치 — PhD_Gil2 views
On Bluesky · 10
- Apr 6, 2026oh-my-claudecode : orchestration multi-agents pour Claude Code, pensée pour des équipes de workers (Codex, Gemini, Claude) qui tournent en… — @camilleroux.com8 likes and reposts · 1 reply
- Mar 31, 2026💎 Hidden Gem! 💎 (1000+ new stars) 📦 Yeachan-Heo / oh-my-claudecode ⭐ 17,120 (+1,785) 🗒 TypeScript Teams-first Multi-agent orchestration… — @github-trending-js.bsky.social2 likes and reposts · 1 reply
- Mar 27, 2026🎉 Celebrating! 🎉 (500+ new stars) 📦 Yeachan-Heo / oh-my-claudecode ⭐ 11,966 (+576) 🗒 TypeScript Teams-first Multi-agent orchestration… — @github-trending.bsky.social2 likes and reposts · 1 reply
- Oct 10, 2026📦 Yeachan-Heo / oh-my-claudecode ⭐ 39,757 (+44) 🗒 TypeScript Teams-first Multi-agent orchestration for Claude Code — @github-trending-js.bsky.social1 likes and repost
- Apr 1, 2026Claude Code使いなら「oh-my-claudecode」は絶対に入れるべき。 複数エージェントをスタックしてタスク実行できる仕組みが神すぎる。特に`/team`コマンドで「プラン→実行→検証→修正」のパイプラインを自動化できるのは、手動作業の次元が違う。… — @woody-ai-tools.bsky.social1 likes and repost
5 more on Bluesky
- Mar 29, 2026今日のGitHubトレンド Yeachan-Heo/oh-my-claudecode Claude Code向けのマルチエージェントオーケストレーションツールです。 Claude Code自体の学習は不要で、簡単に利用できます。… — @dailygithubtrends.bsky.social1 likes and repost
- Mar 28, 2026github.com/Yeachan-Heo/oh-... GitHub - Yeachan-Heo/oh-my-claudecode: Teams-first Multi-agent orchestration for Claude Code — @technews4869.bsky.social1 likes and repost
- Mar 27, 2026oh-my-claudecodeはClaude Code向けのチーム重視型マルチエージェントオーケストレーションツールらしい 複雑なコーディング作業を自動化したい開発者には便利そうかな yug1224 starred Yeachan-Heo/oh-my-claudecode… — @yug1224.com1 likes and repost
- Mar 30, 2026💎 Hidden Gem! 💎 (1000+ new stars) 📦 Yeachan-Heo / oh-my-claudecode ⭐ 16,968 (+1,785) 🗒 TypeScript Teams-first Multi-agent orchestration… — @github-trending.bsky.social0 likes and reposts · 1 reply
- Mar 26, 2026🎉 Celebrating! 🎉 (500+ new stars) 📦 Yeachan-Heo / oh-my-claudecode ⭐ 11,966 (+576) 🗒 TypeScript Teams-first Multi-agent orchestration… — @github-trending-js.bsky.social0 likes and reposts · 1 reply
On the web · 4
- May 20, 2026Yeachan-Heo/oh-my-claudecode v4.14.1 on GitHub — newreleases.io
- Apr 16, 2026Yeachan-Heo/oh-my-claudecode v4.12.0 on GitHub — newreleases.io
- Mar 15, 2026Yeachan-Heo/oh-my-claudecode v4.8.2 on GitHub — newreleases.io
- Feb 5, 2026Yeachan-Heo/oh-my-claudecode v4.0.2 on GitHub — newreleases.io
Used with
Projects with it also use no-comments.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
jaydubya818Skillno-comments
Use when code comments need structural review, root-cause fixes, and constraint encoding.
Also in 5 projects that use this
Other versions16 projects use a version of this.
Word for word · 1
- Yeachan-Heo/oh-my-claude-sisyphus★ 41k100% same
Edited · 4
- overextended/skills★ 2223% same
- anis-dr/skills★ 321% same
- endqwerty/endstack★ 111% same
- Pixxle/skills★ 127% same
Wrote their own version · 11
- umararshad4/honey-stack★ 5same name
- stainless-code/lossless★ 4same name
- jonmumm/skills★ 2same name
- Autocss-com/ai★ 1same name
- Belweave/hstack★ 1same name
- christofferbergj/agent-skills★ 1same name
- pavelsimo/skills★ 1same name
- scottlivingston/claude-skills★ 1same name
- vasu-devs/Forge★ 1same name
- mukco/claude-skills★ 0same name
1 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository90 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- skills/AGENTS.mdAGENTS.md
- src/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- docs/CLAUDE.mdCLAUDE.md
- .github/CLAUDE.mdCLAUDE.md
- commandsSkill
- agent-doc-disciplineSkill
- ai-slop-cleanerSkill
- architectSkill
- architecture-surveySkill
- arenaSkill
- ask-navigatorSkill
- askSkill
- autopilotSkill
- autoresearchSkill
- babysitSkill
- benchmark-checklistSkill
- blast-radiusSkill
- broSkill
- cancelSkill
- configure-notificationsSkill
- correctSkill
- create-formal-verification-skillSkill
- create-verification-skillSkill
- debugSkill
- deepinitSkill
- deep-interviewSkill
- diagramSkill
- drydockSkill
- executeSkill
- external-contextSkill
- figure-it-outSkill
- fix-ciSkill
- fix-merge-conflictsSkill
- get-pr-commentsSkill
- graphSkill
- harborSkill
- hillclimbSkill
- howSkill
- hudSkill
- intentSkill
- interrogateSkill
- in-your-own-wordsSkill
- ketchupSkill
- ketchup-videoSkill
- launchSkill
- loftSkill
- maintain-formal-verification-skillSkill
- maintain-verification-skillSkill
- mapSkill
- minimal-code-disciplineSkill
- minimal-prose-disciplineSkill
- modelsSkill
- omc-doctorSkill
- omc-setupSkill
- personal-modeSkill
- omc-planSkill
- project-session-managerSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 14 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 47
Before writing logic: core types and data structures, scaffold-vs-feature sequencing, what concurrent actors share.
- Distinctive: line 59
When two or more attempted fixes share one assumption and all failed the same gate, stop writing fix three.
- Very specific: line 66
Before sequencing an addition, refactor, or rewrite, remove the dead weight first and build on the simpler base.
- Distinctive: line 105
When stateful logic branches a lot or repeats a shape assumption across files, encode the domain in a structure — a state machine, a typed …
- Distinctive: line 175
Before trusting, reporting, or acting on a measured number, find what limits it and rule out that it measured something other than the work …
- Distinctive: line 206
When delegating, prepend the delegate lane's standing principles to the brief.
- Distinctive: line 227
When this skill is active, name in the reply which principle shaped each non-obvious decision, in one clause.
“Common” is measured: kept by at least 6 in 10 of the 14 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Engineering Principles
Twenty-four principles distilled for OMC's lanes from the pstack principle library (credited above) and rewritten against OMC's own mechanisms. Each names when it applies and which lane carries it. This is a discipline skill: it shapes how work is done; it never gates delivery on its own.
When to use
- a fix has failed twice, or two fixes share one explanation
- debugging, verification, or benchmarking work is starting
- a design choice repeats a shape assumption across files
- delegation prompts are being written and a lane's standing principles should travel with the brief
When not to use
- a one-line mechanical edit with an obvious check
- a hotfix under time pressure — state which principle you skipped and why in one line, then proceed
Core
Laziness Protocol
Refactoring, sizing a diff, or tempted to add abstractions, layers, or
signal threading. Bias to deletion and the smallest change that solves the
problem. Composes with minimal-code-discipline. Carried by executor and
code-simplifier.
Foundational Thinking
Before writing logic: core types and data structures, scaffold-vs-feature
sequencing, what concurrent actors share. Carried by architect and
planner.
Redesign from First Principles
Integrating a new requirement into an existing design. Redesign as if the
requirement had been foundational from day one, instead of patching the old
shape around it. Carried by architect.
Attack the premise
When two or more attempted fixes share one assumption and all failed the
same gate, stop writing fix three. Write the shared assumption down, test
it directly, and let the result choose the next move. Carried by critic
during plan gap analysis and by debugger before a third retry.
Subtract before you add
Before sequencing an addition, refactor, or rewrite, remove the dead weight
first and build on the simpler base. Carried by executor and
code-simplifier.
Minimize reader load
Reviewing or shaping code that is hard to trace. Count layers and hidden
state, collapse one-caller wrappers, shrink mutable scope. Carried by
code-simplifier and writer.
Outcome-oriented execution
Planned rewrites and migrations with explicit phase boundaries. Converge on
the target architecture; do not preserve throwaway compatibility states.
Carried by planner.
Experience first
Product, UX, or feature-scope tradeoffs. Choose user delight over
implementation convenience, and say the tradeoff out loud when you take it.
Carried by designer.
Exhaust the design space
A novel interaction or architectural decision with no precedent. Build 2-3
competing options and compare before committing — the arena and
architect skills are this principle operationalized. Carried by
architect.
Build the lever
Any non-trivial repeated work. Build the tool that does or proves it —
codemod, script, generator — rather than doing it by hand a third time; the
tool is the artifact a reviewer reruns. Carried by executor.
Architecture
Model the domain
When stateful logic branches a lot or repeats a shape assumption across
files, encode the domain in a structure — a state machine, a typed model, a
registry, a reducer — instead of scattering conditionals. OMC's graph
runtime (graph skill) is this principle at full size. Carried by
architect.
Boundary discipline
Wiring validation, error handling, or framework adapters. Guards at system
boundaries, trust internal types, keep business logic pure. Carried by
architect and executor.
Type system discipline
Designing types or signatures in any typed language. Make illegal states
unrepresentable, brand primitives, parse external data at boundaries; in
TypeScript, typescript-best-practices grounds this in syntax. Carried by
architect and executor.
Make operations idempotent
Design commands, lifecycle steps, and loops that run amid crashes and
retries to converge to the same end state. OMC's team recovery replays
worker checkpoints idempotently; user code deserves the same property.
Carried by executor.
Migrate callers, then delete legacy APIs
Introducing a new internal API while old callers exist. Migrate every
caller and delete the old surface in one wave; a compatibility shim with no
expiry is a second system. Carried by executor.
Separate before serializing shared state
Concurrent actors might write the same file, branch, key, or object.
Eliminate the sharing first (a writer per worktree is OMC's house form);
locking is the fallback, not the first move. Carried by executor and
team.
Verification
Prove it works
Done means verified against the real artifact — the command's actual
output, the passing test, the rendered page — never a proxy and never "it
compiles". The verify skill owns the evidence format. Carried by
verifier.
Fix root causes
Trace each symptom to the first place the system went wrong and fix it
there. A guard for a state that should not exist is a workaround, not a
fix; it is legitimate only when that state itself is legitimate. Carried by
debugger; verifier treats symptom-level patches as incomplete work.
Sequence work into verifiable units
Multi-step work — sweeps, migrations, runs of similar edits — and how
commits and PRs stack. Small units that each end in a check, verified
before the next, ordered so the sequence proves itself. Carried by
planner and git-master.
Test behavior, not implementation
Assert what users of the code can observe. A test worth keeping fails when
the behavior breaks and passes when only internals change. Carried by
test-engineer.
Explain the number
Before trusting, reporting, or acting on a measured number, find what
limits it and rule out that it measured something other than the work you
think. Label every claim measured, inferred, or guess in the same sentence.
The benchmark-checklist skill owns the full procedure. Carried by
scientist and by any lane reporting performance.
Delegation
Guard the context window
Route bulk reading and large outputs to subagents; keep summaries in the lead thread. Context spent on a wall of log output is context not spent on judgment. Applies to every lane and to the orchestrator itself.
Never block on the human
Tempted to ask "should I do X?" on reversible work. Proceed, present the result, let the human course-correct; reserve questions for genuine product calls no experiment can settle. Carried by every lane.
Meta
Encode lessons in structure
The second time you write the same instruction, stop writing it a third
time: encode it as a lint rule, a runtime check, a script, or — in OMC — a
learned skill via skillify, or an enforcement via correct. Text rots;
structure reruns. Carried by skillify and self-improve.
Distribution map
When delegating, prepend the delegate lane's standing principles to the brief.
| Lane | Standing principles |
critic | Attack the premise |
debugger | Attack the premise, Fix root causes |
verifier | Prove it works, Fix root causes |
test-engineer | Test behavior, not implementation |
architect | Foundational Thinking, Redesign from First Principles, Model the domain, Exhaust the design space |
planner | Foundational Thinking, Outcome-oriented execution, Sequence work into verifiable units |
executor | Laziness Protocol, Subtract before you add, Make operations idempotent, Boundary discipline, Type system discipline, Migrate callers, Separate before serializing, Build the lever |
scientist | Explain the number |
designer | Experience first |
code-simplifier | Laziness Protocol, Subtract before you add, Minimize reader load |
writer | Minimize reader load |
git-master | Sequence work into verifiable units |
| every lane | Guard the context window, Never block on the human, Encode lessons in structure |
Reporting
When this skill is active, name in the reply which principle shaped each non-obvious decision, in one clause. When a principle and an explicit user instruction conflict, the user wins; say so in one sentence.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

