onboard
Skill2 starsChanged 46 days agoMITView on GitHub
Harmonia onboard - capture an existing repo's canonical verify commands into .harmonia/project.yaml. Use ONLY when explicitly invoked as /harmonia:onboard.
165 other projects use a version of this.
Adopted by
Most recently taken up by
- ggoosen/Digital-Workforcetheir own version, first seen Nov 8, 2026
- joeldevz/skynex-pitheir own version, first seen Nov 8, 2026
- eggs-gd/career-spacetheir own version, first seen Nov 8, 2026
- Codename-11/SubFrametheir own version, first seen Nov 8, 2026
- passion4it-gmbh/passionfruit-sitetheir own version, first seen Nov 5, 2026
- striderZA/OpenCodeGameStudiostheir own version, first seen Nov 4, 2026
Used with
Projects with it also use soak-test, team-live-ops and 10 more.
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.
lilangMaxSkillsoak-test
Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.
Also in 9 projects that use this
lilangMaxSkillteam-live-ops
Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.
Also in 9 projects that use this
HK-hubSkillteach-impeccable
One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.
Also in 19 projects that use this
CoralGameSkillproject-stage-detect
Automatically analyze project state, detect stage, identify gaps, and recommend next steps based on existing artifacts.
Also in 15 projects that use this
CoralGameSkillteam-level
Orchestrate level design team: level-designer + narrative-director + world-builder + art-director + systems-designer + qa-tester for complete area/level creation.
Also in 11 projects that use this
- +5 more from lilangMax
- +2 more from CoralGame
Other versions165 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 165
- Donchitos/Claude-Code-Game-Studios★ 27ksame name
- parcadei/Continuous-Claude★ 3.9ksame name
- parcadei/Continuous-Claude-v2★ 3.9ksame name
- parcadei/Continuous-Claude-v3★ 3.9ksame name
- nateherkai/AIS-OS★ 1.4ksame name
- poshan0126/dotclaude★ 871same name
- talesofai/cohub★ 585same name
- me2resh/apexyard★ 542same name
- nexmoe/DayBee★ 424same name
- nexmoe/eve★ 424same name
155 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.
The file
Files
Your working contract is the rules; their digest is injected at session start - read ${CLAUDE_PLUGIN_ROOT}/core/RULES.md in full only if that digest is not in your context.
Attach Harmonia to a repository it did not scaffold. You capture the repo's own
verify commands into .harmonia/project.yaml so the scoper authors success
criteria against the repo's real commands.
This is not a lifecycle stage: it mints no task workspace and writes no marker or
receipt. It writes exactly one file - .harmonia/project.yaml at the repo root -
which the onboarded repo is meant to commit. On a second run it refines that file
in place; see step 3.
The interview, the run-before-record step, and the refine step are yours to carry out honestly. They are a prose contract, on the same footing as human acceptance today, not a technical guarantee.
The file you write
.harmonia/project.yaml is flat: one scalar per line, known keys only, no nesting
and no arrays, so each value sits on a single physical line.
# .harmonia/project.yaml - this repo's canonical verify commands. Read by the
# scoper. Written by /harmonia:onboard; safe to hand-edit; commit it.
test: <shell command>
lint: <shell command>
typecheck: <shell command>
build: <shell command>Each value is a single bare command on one physical line. The scoper copies it
verbatim into a - run: criterion, so leave no # on a value line - it would
become part of the command. Typical values: go test ./..., npx vitest run, or
bats tests/ for test; golangci-lint run or npm run lint for lint;
tsc --noEmit or npm run typecheck for typecheck; go build ./... or
npm run build for build.
Steps
- Interview for the four verify commands - do not guess them. Elicit this
repo's canonical commands in four categories from the developer:
test,lint,typecheck(ortype-check), andbuild. Ask; do not infer them from a glance at the tree. - Prove each verify command works before recording it. The discipline is: prove it works before recording it. Run each candidate once, from the repo root, and record it only when it exits 0. Reject it on ANY non-zero exit - gate on non-zero, not on an enumerated code set. Judge it by exit status, never by pattern-matching its output. A command that does not run is not written as if it did.
- Refine in place on re-run. One
.harmonia/project.yamlper repo. If the file already exists, read it and update only the keys that changed, preserving the rest; never clobber it from scratch. A second run refines the file in place. Preserving a key is not certifying it: a value you did not receive from the developer this session stays in the file un-run, and you tell them that is what happened. Running it to "check it still works" is executing input you did not author, which is the one thing this step must not do. A repository you cloned can carry this file, and a scoper copies its values verbatim into- run:criteria that execute at review.
A coverage: key left in the file by an earlier version is no longer read by
anything. Tell the developer it is there and that they can delete it.
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.

