planner
AGENTS.md1 starsChanged 37 days agoMITView on GitHub
Planner is built to sit between you and your coding agents: they write plans as files, set Planner up, and show you what they wrote. These docs are written for them as much as for you. Give your agent the planner-setup skill, then ask it to set Planner up. It finds the folders your plans live in, works out how each one is organised, writes the config with planner config add, and runs planner config check until every folder shows…
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 repository4 other files it gives its agents.
- site/llms.txtllms.txt
- link-planSkill
- planner-setupSkill
- visualiseSkill
The file
We split this agents.md into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 17
When an agent links you a plan, each link you click opens another browser tab.
- Very specific: line 35
Copy Markdown: Every page of these docs has a Copy Markdown button that copies the page as Markdown, ready to paste into an agent.
≈ “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.
Files
Working with agents
Planner is built to sit between you and your coding agents: they write plans as files, set Planner up, and show you what they wrote. These docs are written for them as much as for you.
Set Planner up with an agent
Give your agent the planner-setup skill, then ask it to set Planner up. It finds the folders
your plans live in, works out how each one is organised, writes the config with planner config add, and runs
planner config check until every folder shows what is really there.
Without the skill, an agent can do the same from the command line: every config change it
makes is checked, and planner config check exits non-zero until the config is right.
Let agents show you their work
When an agent links you a plan, each link you click opens another browser tab. After a day of tasks that is one tab
per plan, and you lose track of which one is current. Instead, have agents run planner open:
planner open '?ws=my-task/phase-2-api&plan=plan'The plan appears in the Planner tab you already have open, so tabs never pile up. If Planner is not running it starts,
and if no tab is open it opens one. The link-plan skill tells agents to do this every time,
how to build the link, and to put the same link in their message so you can reopen it later.
Have agents write better plans
The visualise skill has an agent write a plan, recap, codebase map, explainer, ELI5 page or
review as one self-contained HTML page in a consistent, readable style, saved where Planner picks it up.
Docs for agents
- Copy Markdown. Every page of these docs has a Copy Markdown button that copies the page as Markdown, ready to paste into
an agent. Agents can also fetch any page as Markdown by adding
.mdto its address, without the trailing slash. - llms.txt.
/llms.txtis a short index of Planner for agents, and/llms-full.txtis every page of these docs, every skill and the config schema in one file. - Schema. The config's JSON schema describes every key.
- HTTP API. A running Planner has a small local API for scripts and agents.
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.