flow
CLAUDE.md39 starsChanged 6 days agoMITView on GitHub
Flow is a Claude Code workflow for a solo developer: global rules (home/), skills (skills/), the flow command and its hooks (scripts/), the text they send the agent (prompts/), the flow-session mod (mods/), a project scaffold (project-template/) and the docs (docs/). Node and bash, the mod in TypeScript. Dependencies are allowed where they save real work (the user, 2026-10-21). ~/.flow/repos/flow links to this checkout, so every edit here runs on this machine at once.
We split this CLAUDE.md into the rules it gives an agent
5 rules. About 0 are common, 0 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
read-the-spec-first: Read docs/spec/product.md and the spec file of the part you touch, before changing skills, installation, the scripts … - Very specific: line 21
never-suggest-upkeep: Never offer /flow:upkeep, and never count the closed tickets waiting for it. - Very specific: line 23
write-locked-decisions: Write a decision the user confirmed with no open threads into its record, batched, with no approval asked. - Very specific: line 26
never-symlink-a-folder: Never symlink ~/.claude/skills/, agents/, rules/ or commands/ as a whole folder. - Very specific: line 33
no-status-in-claude-md: No counts, no dates and no build status here.
≈ “Common” is an estimate: at least 1 in 5 of the 25,680 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Flow, working on the repo
Project
Flow is a Claude Code workflow for a solo developer: global rules (home/), skills (skills/), the flow command and its hooks (scripts/), the text they send the agent (prompts/), the flow-session mod (mods/), a project scaffold (project-template/) and the docs (docs/). Node and bash, the mod in TypeScript. Dependencies are allowed where they save real work (the user, 2026-10-21). ~/.flow/repos/flow links to this checkout, so every edit here runs on this machine at once.
Layout
lab/: the maintainers' workspace: thelab/utilsubmodule, thelab/skillssubmodule (the user's personal skills repository),lab/scripts/(serves this repo alone) andlab/archive/..claude/holds what Claude Code reads here,.flow/what Flow owns.docs/manual/is written for the user alone. Keep it current, and never point a skill or a loaded file at it.~/.flow/wiki/claude-code/downloads/: Claude Code's documentation on disk. Itsllms.txtindexes every page, andWebFetchreaches the rest.pnpm testinsidescripts/runs Flow's suite, andlab/util/has its own.
Rules
designed-is-not-builtA design decided in a ticket changes nothing on disk until its build ticket closes. Until then every file follows the old model: a ticket, a skill or a folder that breaks the new design is the old model at work, never a fault in the file or in the design. Judge a file by the model that wrote it. For the redesign, citefw-16'scontext.mdbefore the spec, which lags it.retire-to-the-archiveRetired code, skills, rules and docs move tolab/archive/with a line in itsREADME.md, never deleted. Ticket text is never archived.not-your-failureA test that still fails with your change stashed belongs to a parallel session: leave it, ticket nothing.read-the-spec-firstReaddocs/spec/product.mdand the spec file of the part you touch, before changing skills, installation, the scripts or the docs tree.never-suggest-upkeepNever offer/flow:upkeep, and never count the closed tickets waiting for it. End with the next ticket instead: each reminder costs the user a line to skip.check-claude-code-updatesWhen asked, runbash lab/scripts/claude-code-changes.shand read each release against Flow. Write what touches Flow into.flow/research/claude-code/releases-read-against-flow.md, ticket each needed change, then set line 1 to the newest release read. Where Flow comes to rely on a newer release, raiseMIN_CLAUDEinscripts/features/machine/prereq.tsand the README's Install line. Download again any page in~/.flow/wiki/claude-code/downloads/pages/whose topic a release changed.write-locked-decisionsWrite a decision the user confirmed with no open threads into its record, batched, with no approval asked. A proposal dropped, by anyone, goes into its ticket or spec file with why, in the same turn.no-code-review-skillReview runs in the same session, never a subagent. Criteria:guides/review-code.mdfor code,guides/write-spec.mdfor the spec.skill-edits-are-liveA skill edit reaches a session at once. Adding, renaming or removing a skill needsflow install.never-symlink-a-folderNever symlink~/.claude/skills/,agents/,rules/orcommands/as a whole folder.flow installlinks per item. The plugin folderflow/is the one folder link.one-source-two-waysEvery shipped script lives once, inscripts/: bash where it wraps another command, Node where there is real logic.lab/scripts/holds the ones that serve this repo alone. Never copy a file, and never let alab/path leak into a skill,home/orproject-template/.home-files-exist-twicehome/CLAUDE.mdandhome/settings.jsonare the public templates,~/.flow/CLAUDE.mdand~/.claude/settings.jsonthe personalized copies, and this file is neither. Never write personal content into this repo. Always carry an edit to one copy across to its twin by hand, in the same turn and whichever way it was made. The same holds for any other file with a twin: look inhome/andproject-template/before finishing. Only a line that is personal stays out, and the reply names it. A setting with no template line, such aswrapUpAtin~/.flow/settings.json, goes to the default the code reading it uses.agent-text-in-markdownA guide a mod or hook sends the agent lives in its own.mdfile inprompts/, named for what it says. Short lines, and text the code assembles from conditions, stay in the code.docs/manual/shows each one as the agent receives it.measurements-in-fw-294A check that can run only once real sessions exist is one line infw-294's## Tasks: the ticket it checks, the baseline, the target. Then the building ticket can close. Never leave the check open in that ticket, where nobody runs it after the close.measure-real-workA check runs through/flow:auditon sessions of real work, once days of them exist. Never stage a replay or a test session to measure, and never make a ticket for a measurement.
record-notable-toolsA tool, skill or service met in research that stands out → one entry in.flow/research/tool-library/notable-tools.md: what it does, what it costs, why it stands out, the job it could do here. Only standouts: the toolboxfw-94dropped filled with tools no work needed. Holds untilfw-62's library exists.no-status-in-claude-mdNo counts, no dates and no build status here. What Flow does goes indocs/spec/, open work in tickets.
Temporary
flow-under-repairFlow is under repair (fw-361): treat its skills and rules as possibly broken. Follow a step where it helps the work, and skip one that makes it worse, saying so in one line. Distrust most:/flow:groundwork, the path for writing a skill, and the rules on proposals and capture.discuss-without-groundworkDesign by plain discussion: ask the questions that matter, propose with a recommendation, wait for the answer. Never run groundwork's phases unless the user asks for them.
Flow runs on this machine alone. A second machine joins soon, once this version of Flow is finished. Never suggest setting it up or running anything for it. Design every change so state that follows a ticket or a project syncs, and the other machine sees it. Sync faults such as git conflicts belong to the multi-machine tickets (fw-6, fw-158), never to the change at hand. Delete this section when the machine joins.
In this repository14 other files it gives its agents.
- home/CLAUDE.mdCLAUDE.md
- project-template/CLAUDE.mdCLAUDE.md
- auditSkill
- researchSkill
- upkeepSkill
- handoffSkill
- startSkill
- visualizeSkill
- debugSkill
- executeSkill
- groundworkSkill
- review-codeSkill
- tickets-from-specSkill
- write-specSkill
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.

