wp-agent-harness
AGENTS.md0 starsChanged 13 days agoMITView on GitHub
Canonical narrative + tables: docs/AGENTS.md. This repo-root mirror exists for tools that only read AGENTS.md at the repository root. For the full documentation index, commands, and domain rules, open docs/AGENTS.md. Maintenance: When stack pins, commands, or skill triggers change, update this file together with CLAUDE.md and .cursor/AGENTS.md. See docs/agents/agent-contract.md (Cross-tool parity). Local, disposable WordPress harness for coding agents. Docker Compose runs WordPress and MariaDB on loopback; agents talk to a real site over the official WordPress MCP Adapter. This repository…
- Reads credentials
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 31,700 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 repository16 other files it gives its agents.
- .cursor/AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- site/llms.txtllms.txt
- wordpress-routerSkill
- wp-abilities-apiSkill
- wp-abilities-auditSkill
- wp-abilities-verifySkill
- wp-block-developmentSkill
- wp-block-themesSkill
- wp-patternsSkill
- wp-plugin-developmentSkill
- wp-project-triageSkill
- wp-rest-apiSkill
- wp-wpcli-and-opsSkill
The file
We split this AGENTS.md into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Distinctive: line 7
Maintenance: When stack pins, commands, or skill triggers change, update this file together with CLAUDE.md and .cursor/AGENTS.md.
- Very specific: line 51
Never add agent attribution (Co-authored-by: Cursor, @cursoragent, Made/Generated with Cursor).
≈ “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
Agents (Agent Harness for WordPress)
Canonical narrative + tables: docs/AGENTS.md.
This repo-root mirror exists for tools that only read AGENTS.md at the repository root. For the full documentation index, commands, and domain rules, open docs/AGENTS.md.
Maintenance: When stack pins, commands, or skill triggers change, update this file together with CLAUDE.md and .cursor/AGENTS.md. See docs/agents/agent-contract.md (Cross-tool parity).
What this repo is
Local, disposable WordPress harness for coding agents. Docker Compose runs WordPress and MariaDB on loopback; agents talk to a real site over the official WordPress MCP Adapter. This repository does not ship an MCP server, abilities framework, or WordPress plugin of its own. The WordPress harness is localhost-only (not a production WordPress deploy); site/ is the public marketing page. Connecting an agent to a separate live site is outside the harness: remote-site.md.
Stack pin
WordPress|7.1.3 (image wordpress:7.1.3-php8.3-apache) | PHP 8.3 | Apache 2.4
MariaDB|11.8.9
MCP Adapter|0.7.1 (GitHub release ZIP)
MS WordPress Abilities|1.13.0 (GitHub release ZIP)
WP-CLI|2.12.0 + ability-command 1.0.4
MCP|meta-tools: discover / get-ability-info / execute-ability
Ports|127.0.0.1 only (WP + DB)Common mistakes:
- Inventing ability names or parameters instead of
discover→get-ability-info→execute. - Treating
docker-compose.yml/bin//.envas site content and editing them for a content task. - Publishing, deleting, or bulk-changing without an explicit ask (default to drafts).
- Putting credentials in a tracked file, or binding ports to
0.0.0.0. - Switching the local site to
@wordpress/env, Playground, or Blueprints.
Commands (repo root)
| Task | Command |
| Provision (idempotent) | ./bin/setup |
| Register MCP (Claude Code) | ./bin/connect |
| Print MCP URL + auth export | ./bin/connect --print (Codex / Cursor / any client) |
| Health | ./bin/status |
| WP-CLI / abilities without MCP | ./bin/wp … / ./bin/wp ability list |
| PHP debug log | ./bin/logs --debug |
| Demo content | ./bin/seed (--remove to delete it) |
| Write abilities agents have called | ./bin/audit |
| Tests layers 0–3 | ./bin/test --skip-claude |
| Destroy volumes | ./bin/reset (explicit ask only) |
Git and PR rules (summary)
- Branch from
developfor day-to-day PRs; release cuts merge intomain. One subject per PR. Template:.github/PULL_REQUEST_TEMPLATE.md. - Never add agent attribution (
Co-authored-by: Cursor,@cursoragent, Made/Generated with Cursor). - Changelog: behaviour agents rely on →
## [Unreleased]inCHANGELOG.md.
Full detail: docs/AGENTS.md, docs/agents/agent-contract.md.
Key docs
| Topic | File |
| Full index + domain | docs/AGENTS.md |
| Task contract | docs/agents/agent-contract.md |
| Risk tiers | docs/agents/runtime-policy.md |
| Abilities | docs/abilities.md |
| AI skills map | docs/ai-skills.md |
| Architecture | docs/architecture.md |
| Claude Code MCP | docs/claude-code.md |
| Codex MCP | docs/codex.md |
| Examples | examples/README.md |
| LLM entry | llms.txt |
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.