archeflow / rules
Cursor rule0 starsChanged 52 days agoMITView on GitHub
ArcheFlow role-based Plan/Do/Check/Act workflows. Use when the user invokes /archeflow-run, /archeflow-review or /archeflow-sprint, or asks for an ArcheFlow run, review or sprint.
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 4,144 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository29 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- archeflow-reviewSkill
- archeflow-runSkill
- 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 archeflow.mdc 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 31
Call lib/archeflow-*.sh with the Shell tool from the project root, using the absolute path of the ArcheFlow checkout.
≈ “Common” is an estimate: at least 1 in 5 of the 6,668 Cursor rule 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
--- description: ArcheFlow role-based Plan/Do/Check/Act workflows. Use when the user invokes /archeflow-run, /archeflow-review or /archeflow-sprint, or asks for an ArcheFlow run, review or sprint. globs: alwaysApply: false --- # ArcheFlow in Cursor ArcheFlow is a set of skills (Markdown instructions) plus Bash helpers in `lib/`. In Cursor the core skills are loaded through three adapters in `.cursor/skills/`: | Command | Adapter | Core skill | |---------|---------|------------| | `/archeflow-review` | `.cursor/skills/archeflow-review/` | `skills/review/SKILL.md` | | `/archeflow-run <task>` | `.cursor/skills/archeflow-run/` | `skills/run/SKILL.md` | | `/archeflow-sprint` | `.cursor/skills/archeflow-sprint/` | `skills/sprint/SKILL.md` | For the other functions, read the core skill and follow it: `skills/init/`, `skills/status/`, `skills/report/`, `skills/dag/`, `skills/replay/`, `skills/score/`, `skills/memory/`, `skills/scan/` (the Claude Code names are `/archeflow:<name>`). ## Agents Where a skill spawns `archeflow:<role>`, use `Task(subagent_type="generalPurpose", prompt="<full text of agents/<role>.md>\n\n---\n\n<prompt>")`. Spawn parallel reviewers as several `Task` calls in one message. Give each agent only the inputs the skill lists for its role. ## Scripts Call `lib/archeflow-*.sh` with the Shell tool from the project root, using the absolute path of the ArcheFlow checkout. They need Bash 4+, jq 1.6+ and git. Never paste task text or agent output into a shell command; write it to a file first, as the skills describe. ## Skip ArcheFlow For single-line fixes, questions, reading code, config tweaks and plain git operations.
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.