agentleFS
zademyzademy/lu-query/AGENTS.md

lu-query

AGENTS.md2 starsChanged 29 days agoMITView on GitHub

Issues live in GitHub Issues (zademy/lu-query); use the gh CLI. See docs/agents/issue-tracker.md. The five canonical triage roles use their default label strings (needs-triage, needs-info, ready-for-agent, ready-for-human, wontfix). See docs/agents/triage-labels.md. Single-context: one GLOSSARY.md and docs/adr/ at the repo root. See docs/agents/domain.md. One path: feature branch -> PR into develop -> PR develop -> master (release). Branch protection rejects direct pushes to develop and master (PR required, zero approvals, admins included) — every change rides a PR, however small. Merge PRs with…

The file

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

6 rules. About 0 are common, 3 are distinctive, and 3 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.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before every commit, run the whole local gate, not just the files you touched: npm run format:check (prettier checks the entire repo and CI …

    line 25
  2. Distinctive:

    Only an explicit choice of antislop during or after selects a session mode.

    line 37
  3. Distinctive:

    Use the overview to decide whether to search, read, create, or update Backlog tasks.

    line 58
  4. Distinctive:

    Before task lifecycle actions, read the matching detailed guide:

    line 60
  5. Very specific:

    Use backlog <command> --help before running unfamiliar commands.

    line 65
  6. Very specific:

    Do not edit Backlog task, draft, document, decision, or milestone markdown files directly.

    line 67

≈ “Common” is an estimate: at least 1 in 5 of the 41,581 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

Agent skills

Issue tracker

Issues live in GitHub Issues (zademy/lu-query); use the gh CLI. See docs/agents/issue-tracker.md.

Triage labels

The five canonical triage roles use their default label strings (needs-triage, needs-info, ready-for-agent, ready-for-human, wontfix). See docs/agents/triage-labels.md.

Domain docs

Single-context: one GLOSSARY.md and docs/adr/ at the repo root. See docs/agents/domain.md.

Git flow

One path: feature branch -> PR into develop -> PR develop -> master (release). Branch protection rejects direct pushes to develop and master (PR required, zero approvals, admins included) — every change rides a PR, however small.

Merge PRs with "Create a merge commit" — the only method enabled; squash and rebase are disabled repo-wide. A squashed release PR freezes the merge-base and the next release PR conflicts (#61 was the incident).

The PR branch deletes itself after merge (auto-delete); develop survives it, protected from deletion because it is the release PR's head. Local copies need git branch -D; a remote delete or fetch --prune never removes them.

A release: bump package.json by PR into develop first, then PR develop -> master. release and publish are idempotent — an existing v<version> tag or npm version ends the run as a notice, publishing nothing. CI layout lives in CONTRIBUTING.md ("Pipeline de CI").

Before every commit, run the whole local gate, not just the files you touched: npm run format:check (prettier checks the entire repo and CI will too), npm run lint, npm run typecheck, npm test, npm run build. A green check on a subset of files is not a green gate.

<!-- antislop:start -->

antislop

For UI, copy, people, mobile layout, or code comments work, read these installed skill files directly (use these paths even if a same-named global skill exists):

  • Core filter, always on: antislop: .opencode/skills/antislop/SKILL.md
  • UI / visual: antislop-ui: .opencode/skills/antislop-ui/SKILL.md
  • Copy & text: antislop-copywriting: .opencode/skills/antislop-copywriting/SKILL.md
  • People: antislop-human: .opencode/skills/antislop-human/SKILL.md
  • Mobile / responsive: antislop-layoutmobile: .opencode/skills/antislop-layoutmobile/SKILL.md
  • Code comments: antislop-code: .opencode/skills/antislop-code/SKILL.md Before starting, follow the core's "Two Usage Modes" section in strict order: explicit session instruction first, then global preference, then ask. A session instruction always wins. For a resolved mode, say antislop active: <mode> (session override). or antislop active: <mode> (global preference). once before presenting findings or making edits, using the actual mode and source. Acknowledging the user's request without naming the source does not replace this notice. Only an explicit choice of antislop during or after selects a session mode. A request to review, audit, or avoid file edits does not select a mode; read the global preference in that case. Another skill's mode does not select antislop's mode. If the mode is unresolved, ask during/after and end the response; wait for the answer before any UI review, planning, or concept. For read-only tasks, put the active-mode notice only at the start of the final answer, never in progress messages. For editing tasks, announce before the first edit and omit it from the final answer. To update antislop later: npx antislop-ai --update, or run npx antislop-ai and pick Overwrite them.
<!-- antislop:end --><!-- groma:start -->

Groma

This project uses Groma. Before you scan, inspect, or curate architecture, or change files for a Backlog task, run groma agent-instructions and read the guide it names for that job. When it reports a first scan, ask the user whether they want you to curate the architecture. Do not edit Groma-owned architecture files directly.

<!-- groma:end --><!-- BACKLOG.MD GUIDELINES START --><!-- backlog.md-instructions-version: 1.55.0 -->

<CRITICAL_INSTRUCTION>

Backlog.md Workflow

This project uses Backlog.md for task and project management.

At the beginning of each conversation in this project, run backlog instructions overview before answering or taking action. Re-read it only if you have not read it yet in the current conversation.

Use the overview to decide whether to search, read, create, or update Backlog tasks.

Before task lifecycle actions, read the matching detailed guide:

  • backlog instructions task-creation before creating or splitting tasks
  • backlog instructions task-execution before planning, changing status or assignee, adding a plan or implementation notes, or implementing task work
  • backlog instructions task-finalization before checking acceptance criteria, writing final summaries, or moving tasks to terminal statuses

Use backlog <command> --help before running unfamiliar commands. Help shows options, fields, and examples.

Do not edit Backlog task, draft, document, decision, or milestone markdown files directly. Use the backlog CLI so metadata, relationships, and history stay consistent.

</CRITICAL_INSTRUCTION>

<!-- BACKLOG.MD GUIDELINES END -->

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.