archeflow-run
Skill0 starsChanged 52 days agoMITView on GitHub
Run one task through ArcheFlow's Plan, Do, Check, Act on its own git branch (Cursor adapter for the core run skill). Usage: /archeflow-run <task> [--workflow fast|standard|thorough] [--dry-run] [--start-from plan|do|check|act]
In this repository29 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .cursor/rules/archeflow.mdcCursor rule
- archeflow-reviewSkill
- archeflow-sprintSkill
- act-phaseSkill
- autonomous-modeSkill
- check-phaseSkill
- cost-trackingSkill
- custom-archetypesSkill
- dagSkill
- domainsSkill
- git-integrationSkill
- initSkill
- memorySkill
- multi-projectSkill
- presenceSkill
- progressSkill
- replaySkill
- reportSkill
- reviewSkill
- runSkill
- scanSkill
- scoreSkill
- shadow-detectionSkill
- sprintSkill
- statusSkill
- templatesSkill
- using-archeflowSkill
- workflow-designSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Read <archeflow-root>/skills/run/SKILL.md and follow it.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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
ArcheFlow Run (Cursor)
Read <archeflow-root>/skills/run/SKILL.md and follow it. The Maker works in the worktree
that archeflow-git.sh worktree creates: tell the Maker's Task to cd to that path for every
command. Cursor has no isolation parameter, and none is needed.
Find <archeflow-root>
The ArcheFlow checkout: the directory that contains lib/archeflow-event.sh, skills/ and
agents/. If this file is <root>/.cursor/skills/<name>/SKILL.md, it is three levels up.
Otherwise ask the user where their ArcheFlow checkout is. Use its absolute path for every
<archeflow-root> below and in the loaded skill.
Cursor tool mapping
| The core skill says | In Cursor |
spawn an agent with subagent_type: "archeflow:<role>" | Task(subagent_type="generalPurpose", prompt="<full text of <archeflow-root>/agents/<role>.md>\n\n---\n\n<the prompt from the skill>") |
| spawn several agents in one message | several Task calls in one message |
| run a command | Shell(command="..."), from the project root |
| write a file with your file tool | Write |
Everything else (steps, commands, artifacts, confirmations) is exactly as in the core skill.
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.