mdiri-aimdiri-ai/SoduWork/AGENTS.md

SoduWork

AGENTS.md930 starsChanged 6 days agoMITView on GitHub

This public guide supplements CONTRIBUTING.md. Read the relevant component guide before changing its interfaces. From the root, run sh start.sh --desktop on macOS/Linux, .\start.cmd --desktop in Windows PowerShell, or start.cmd --desktop in Command Prompt. Follow the startup guide for prerequisites and isolated data directories. Use synthetic data and test accounts for validation. See the developer guide, CI guide, release scope and security policy for details.

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 31,439 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 repository38 other files it gives its agents.
- agent-product-designSkill
- app-developerSkill
- brainstormingSkill
- browser-useSkill
- codebase-designSkill
- code-reviewSkill
- computer-useSkill
- delivery-checkSkill
- diagnosing-bugsSkill
- dispatching-parallel-agentsSkill
- domain-modelingSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- frontend-designSkill
- grillingSkill
- grill-with-docsSkill
- improve-codebase-architectureSkill
- mcp-studioSkill
- mcp-toolsSkill
- officeSkill
- pptxSkill
- product-incubatorSkill
- prototypeSkill
- receiving-code-reviewSkill
- requesting-code-reviewSkill
- resolving-merge-conflictsSkill
- skill-studioSkill
- subagent-driven-developmentSkill
- systematic-debuggingSkill
- taskSkill
- tddSkill
- test-driven-developmentSkill
- using-git-worktreesSkill
- using-superpowersSkill
- verification-before-completionSkill
- wizardSkill
- writing-plansSkill
- writing-skillsSkill

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:
Keep paired English and Chinese documentation and their language links in sync.
line 20
Very specific:
Keep credentials, private addresses, user data, logs, screenshots, build outputs and dependency caches out of commits.
line 21

≈ “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

Working on SoduWork

This public guide supplements CONTRIBUTING.md. Read the relevant component guide before changing its interfaces.

Repository and local startup

client/ contains the Electron desktop, main-process services, IPC bridge and renderer.
hub-backend/ contains the FastAPI Hub, database migrations and Runner.
hub-frontend/ contains the React/Vite administration UI.
skills/, ops/self-host/ and tools/ contain bundled skills, deployment and verification tools.

From the root, run sh start.sh --desktop on macOS/Linux, .\start.cmd --desktop in Windows PowerShell, or start.cmd --desktop in Command Prompt. Follow the startup guide for prerequisites and isolated data directories. Use synthetic data and test accounts for validation.

Changes and checks

Preserve existing user changes and data. Add Alembic migrations for database schema changes.
Run checks for the component you change. In client/, run npm test. In hub-frontend/, run npm run build and node --test tests/*.test.mjs. For backend checks, inspect python3 quality_gate.py --help in hub-backend/. For launcher changes, run python3 -m unittest tools.dev.test_start_local at the root. On Windows, use py for standalone Python commands, or python inside the activated environment.
At the root, run node tools/check-public-source.cjs, node tools/check-third-party.cjs, node tools/check-docs.cjs and python3 tools/security/scan_secrets.py --download.
Review and stage added public files. Git tracks the development inventory; do not generate or commit SOURCE-MANIFEST.json. The source exporter generates it inside each archive from the committed files.
Keep paired English and Chinese documentation and their language links in sync. Directory entry points are English README.md and Chinese README.zh-CN.md.
Keep credentials, private addresses, user data, logs, screenshots, build outputs and dependency caches out of commits. Public source inclusion is governed by PUBLIC-SOURCE.json.
Sign off commits under the DCO with git commit -s. In pull requests, describe the behavior change, checks actually run, platforms tested and remaining gaps.

See the developer guide, CI guide, release scope and security policy for details.

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