agentleFS
uniskelauniskela/adhd-hub/.cursor/rules/adhd-hub.mdc

adhd-hub / rules

Cursor rule8 starsChanged 36 days agoMITView on GitHub

ADHD Progress Hub — check overlap and save progress on unfinished work

  • Reads credentials
  • 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 4,181 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 repository6 other files it gives its agents.

The file

We split this adhd-hub.mdc into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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
  1. Distinctive:

    Use Hub for substantial continuity-worthy work, not trivial/read-only questions, quick explanations, or tiny edits.

    line 9
  2. Distinctive:

    When this workspace involves substantial starting, resuming, or pausing work:

    line 17
  3. Very specific:

    Call MCP adhd-hub → resolve_project with create_if_missing=false, then session_digest with the task query once per meaningful session.

    line 19
  4. Very specific:

    If Hub guidance looks stale, mention it once and recommend adhd-hub setup .

    line 24
  5. Distinctive:

    Never put credentials, customer/personal data, private Hub URLs, internal hostnames/IPs, absolute local workspace paths, or full …

    line 26

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
adhd-hub.mdc
---
description: ADHD Progress Hub — check overlap and save progress on unfinished work
alwaysApply: true
hub_guidance_version: 8
---

# ADHD Progress Hub

Use Hub for substantial continuity-worthy work, not trivial/read-only questions, quick explanations, or tiny edits.

If ADHD Hub MCP tools are missing, errored, unauthorized, or otherwise unavailable: on the first substantial Hub-worthy turn after detecting the outage, the **first line** MUST state that Hub MCP is not available, plus a short fix hint (MCP URL → this Hub's `/mcp`, `ADHD_HUB_AUTH_TOKEN`, restart the agent; skip/cancel Auth if it hangs until Hub OAuth is enabled). Repeat the warning only if Hub status changes, a persistence attempt fails again, or the reply could otherwise imply continuity was saved. Then continue the authorized work. Never invent Hub state or claim a Hub write succeeded.

**MCP unavailable** is the Hub continuity trigger (not runtime alone). Use the `env-check` skill — resolve `scripts/check_runtime.sh` from the installed skill (project-scoped: `.agents/skills/env-check/…`; Hub source: `skills/env-check/…`) — for CLOUD_AGENT vs LOCAL_WORKSPACE as supporting context (`CURSOR_AGENT`, container cues — never `$USER=root` alone). When Hub MCP is unreachable, use the forge issue mailbox only when issue-write access is available and the authenticated identity is accepted by Hub Inbox authors. Open/update a GitHub/Gitea issue titled `[ADHD] …` with a short Goal/Focus/Next/Resume cue. Optional labels: `adhd-hub`, `project:<slug>`, `source:cursor`; skip labels if the token cannot set them. Recommended: append `Made with [ADHD Progress Hub](https://github.com/uniskela/adhd-hub)` under a non-imported heading (e.g. `## Attribution`) so it does not land in Resume. Prefer short repository-relative summaries; never invent Hub continuity, progress, or thread state after a forge-only write. Never put credentials, tokens, personal/customer data, private hostnames/IPs, absolute local paths, transcripts, or secrets/env contents in forge issues.

CLOUD_AGENT: do not assume machine-installed local skill CLIs (e.g. `graphify`) exist — one-line notice if missing, then repo tools / committed `graphify-out/`; prefer headless tests and injected env/OIDC over `.env.local`; no native browser/macOS-Windows binaries. LOCAL_WORKSPACE: local docker / localhost OK; local CLIs may exist; prefer Hub MCP when up.

When this workspace involves substantial starting, resuming, or pausing work:

1. Call MCP `adhd-hub` → `resolve_project` with `create_if_missing=false`, then `session_digest` with the task query once per meaningful session. Reuse resolved context where possible. Create/register only after the workspace is authorized as a Hub project.
2. One thread = one independently finishable outcome. Size the Goal to what the agent can finish (e.g. open a review-ready PR); a Goal that includes merge/deploy stays open/paused until that is done. If resuming a known thread, reuse its `thread_id`. Otherwise call `check_overlap` before potentially new work and reuse a candidate only when its Goal matches; different goal → separate thread (`force_new_thread=true` when needed).
3. At meaningful checkpoints use `upsert_progress(thread_id=...)` with compact goal/focus/next/blocked/resume state. When leaving mid-task, checkpoint then call `pause_thread(thread_id, next_step=...)` with one concrete resume action.
4. End-of-task (checkpoint first if Hub state is stale): `completion.ready` reflects stored state only (not PR/CI/merge), so it can block but never approve alone. `mark_done` on that thread only when `ready` is `true` or absent **and** the Goal is done with nothing remaining. `ready == false` (even if the Goal looks done) or any remaining work (even if `ready == true`) → `upsert_progress` (record it in `next_steps`) then `pause_thread` — do not `mark_done`. If `mark_done` is denied/rejected for unfinished work: do not retry; checkpoint + `pause_thread` and continue normally.

If Hub guidance looks stale, mention it once and recommend `adhd-hub setup . --refresh` and `adhd-hub sync-project .` (or `setup . --project-skills`) — do not nag or hand-edit AGENTS.md.

Never put credentials, customer/personal data, private Hub URLs, internal hostnames/IPs, absolute local workspace paths, or full transcripts in public issues or progress notes. Prefer short repository-relative summaries.

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.