agentleFS
Sign inStart free
FalseFoundationFalseFoundation/taskset/AGENTS.md

taskset

AGENTS.md1 starsChanged 5 months agoMITView on GitHub

Use Taskset to plan, research, decide, operate, and track repository work as Markdown under .taskset/. Link related entities with --related. Keep scratch checklists in the task body. Promote durable memory into documents mid-work. Project or global installs also expose the taskset binary. Do not require pnpm taskset. - Canonical state is .taskset/**/*.md - Prefer CLI mutations over hand-editing canonical files when a command exists - Commands and --related use short hex id values (a1b2c3). Filename sequence prefixes (0000001-…) are display…

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,774 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 repository3 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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
  1. Very specific:

    Use Taskset to plan, research, decide, operate, and track repository work as Markdown under .taskset/.

    line 3
  2. Distinctive:

    Prefer CLI mutations over hand-editing canonical files when a command exists

    line 45
  3. Distinctive:

    Create follow-up tasks or checklist subtasks for newly discovered work

    line 53
  4. Distinctive:

    Create research, decision, runbook, story, flow, lesson, concern, or audit documents for durable evidence, choices, and operational memory

    line 54
  5. Distinctive:

    Keep statuses current mid-work

    line 55

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

Taskset agent guide

Use Taskset to plan, research, decide, operate, and track repository work as Markdown under .taskset/.

What to write where

NeedKindCommand sketch
User outcomestorytaskset document create story --title "…"
Journey / variantsflowtaskset document create flow --title "…"
Evidence and optionsresearchtaskset document create research --title "…"
Lasting choicedecision / adrtaskset document create adr --title "…"
Recovery procedurerunbooktaskset document create runbook --title "…"
Recurring mistake / patternlessontaskset document create lesson --title "…"
Open residual riskconcerntaskset document create concern --title "…"
Spot-check / inventoryaudittaskset document create audit --title "…"
Executable worktasktaskset task create --title "…"
Program healthparent tasktaskset task program <parent-id> --json

Link related entities with --related. Keep scratch checklists in the task body. Promote durable memory into documents mid-work.

Install and invoke

npx @taskset/cli@latest init
npx @taskset/cli document list --json
npx @taskset/cli task list --json
pnpm dlx @taskset/cli doctor --json
yarn dlx @taskset/cli sync --json
bunx @taskset/cli document show your_document_id_here --json

Project or global installs also expose the taskset binary. Do not require pnpm taskset.

Discovery

  • Repository marker: nearest .taskset/ directory
  • Optional overlay: taskset.config.ts at that root
  • Missing config: built-in defaults
  • taskset init creates .taskset/; --config writes optional config

Rules

  • Canonical state is .taskset/**/*.md
  • Prefer CLI mutations over hand-editing canonical files when a command exists
  • Commands and --related use short hex id values (a1b2c3). Filename sequence prefixes (0000001-…) are display metadata only—never identity.
  • Markdown hyperlinks to docs, skills, or .taskset/ files must use the repository-relative filepath (for example docs/memory-model.md or .taskset/decisions/0000003-…-81c92d.md). Do not use a bare hex id as a link target.
  • Prefer --json
  • Create follow-up tasks or checklist subtasks for newly discovered work
  • Create research, decision, runbook, story, flow, lesson, concern, or audit documents for durable evidence, choices, and operational memory
  • Keep statuses current mid-work

Read next

  • Agent guide
  • Agent workflows
  • Agent commands
  • Query recipes
  • Document types
  • Memory model
  • Taskset skill
  • CLI reference

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free