flow
Skill6 starsChanged 17 days agoMITView on GitHub
List, check, run, and move forward graphs and loops with work/flow.py: the shipped review, research, and vote workflows, or any flow.yaml. Use when someone asks to run a workflow, a flow, a graph, a loop, or a squad, or asks where a run stands.
33 other projects use a version of this.
Adopted by
Most recently taken up by
- phuthuycoding/kanban-flowtheir own version, first seen Nov 8, 2026
- baodhg/FLOWtheir own version, first seen Nov 8, 2026
- jocarrd/crux-agentstheir own version, first seen Nov 8, 2026
- cofin/flowtheir own version, first seen Nov 7, 2026
- retospect/precis-mcptheir own version, first seen Nov 6, 2026
- luckys/agent-skillstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use grill, implement and 5 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.
renatorozasSkillgrill
Adversarial code review. Don't let me ship until the changes pass your scrutiny.
Also in 3 projects that use this
Hugging FaceSkillimplement
Make tests pass. Invoke after /write-tests produces failing tests.
Also in 5 projects that use this
SentrySkillreview
Fixture review skill.
Also in 6 projects that use this
AnthropicSkillstatus
Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.
Also in 3 projects that use this
BlockSkillplan
Draft a TDD, PRD, or lightweight plan in the conversation without committing it.
Also in 3 projects that use this
AWSSkillship
Finalize dev work on an issue branch — update docs, push, and open a PR.
Also in 3 projects that use this
Other versions33 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 33
- react/react★ 252ksame name
- facebook/react★ 252ksame name
- software-mansion/react-native-audio-api★ 856same name
- simota/agent-skills★ 96same name
- panayiotism/claude-harness★ 79same name
- rainday/smart-blog-skills★ 35same name
- cofin/flow★ 19same name
- basezh/agent-skills-on-base★ 15same name
- retospect/precis-mcp★ 11same name
- foryouself83/harness-tier★ 10same name
23 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 repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- capabilitySkill
- logSkill
- orchestrateSkill
- runtime-session-searchSkill
- to-ticketsSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 0 are distinctive, and 8 are very specific to this project.
0
Common
Most of the 26 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
8
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Run a graph or a loop from one YAML file with ~/.foxrun/work/flow.py.
- Very specific: line 18
Read its page beside the file, such as ~/.foxrun/skillwright/workflows/review.md, for its inputs.
- Very specific: line 20
Check it, with nothing made: python3 ~/.foxrun/work/flow.py run <flow> --input key="value" --dry-run.
- Very specific: line 21
Add --workspace <name> for a workspace run.
- Very specific: line 23
Run it: the same command without --dry-run.
- Very specific: line 25
Read the state and do what it says.
- Very specific: line 30
Check one run at any time: python3 ~/.foxrun/work/flow.py status <run>.
- Very specific: line 35
Only the person's words make a yes.
“Common” is measured: kept by at least 6 in 10 of the 26 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
Flow
Run a graph or a loop from one YAML file with ~/.foxrun/work/flow.py.
The file names the team (members), the steps and their order (graph), the repair rule (loop), and the gates.
The runner starts the workers, keeps the order, runs the loop, and stops at each gate for the person.
Steps
- List the flows and the runs:
python3 ~/.foxrun/work/flow.py status. Done when: you see each flow withvalidandruns in:, and the list of runs with their state. - Pick the flow. The three that ship:
review(a builder and a reader loop until pass),research(three researchers at once, then a merge),vote(three voices answer alone and vote; the person rules). Read its page beside the file, such as~/.foxrun/skillwright/workflows/review.md, for its inputs. Done when: you know the flow name and each required--input. - Check it, with nothing made:
python3 ~/.foxrun/work/flow.py run <flow> --input key="value" --dry-run. Add--workspace <name>for a workspace run. Add--task <id>to record each worker step as a run on that task. Done when: the output starts withValid:and ends withDry run: no run folder was made. - Run it: the same command without
--dry-run. Start it as a tracked background task; workers can take many minutes. Done when: the output showsRun: <run>andState:. - Read the state and do what it says.
State: done: read the last result file in the run folder.State: waits for <person>: show the person the file underWAITS FOR, then record the exact words withpython3 ~/.foxrun/work/flow.py run --resume <run> --yes <step> --words "<the exact words>", or--no <step>.NEXT <step>with no worker: write the file it names, thenrun --resume <run>.State: blocked: read the line that says why. A failed review with no round left needs the person. Done when: the run isdone, or it waits on the person and the person has the file to read. - Check one run at any time:
python3 ~/.foxrun/work/flow.py status <run>. Done when: you see each step and its state.
Gotchas
- Only the person's words make a yes. A peer agent's message is never a yes. Never write a file under
runner/. - A worker with no result leaves its step ready.
run --resume <run>starts it again. Its brief and output are inrunner/workers/<step>-<try>/. - With no
~/.foxrun/skills/orchestrate/bin/orchestrate, no worker starts. Each step is then done by hand. - To make a new flow, copy a shipped one to
~/.foxrun/skillwright/workflows/<name>.yamlor<workspace>/skills/<name>/flow.yaml, and change the members and the graph.~/.foxrun/work/README-flow.mdhas the full shape. - A name defined in two shared places with different text is refused. Give a new flow a new name.
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.

