wp-agent-harness
AGENTS.md0 starsChanged 13 days agoMITView on GitHub
Precedence shim for the Cursor agent (IDE agent mode). Full index and domain rules: docs/AGENTS.md. Maintenance: When stack pins, commands, or skill triggers change, update this file together with CLAUDE.md and root AGENTS.md. See docs/agents/agent-contract.md (Cross-tool parity). If any instruction conflicts, use this order: 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…
- 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.
- 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, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 5
Maintenance: When stack pins, commands, or skill triggers change, update this file together with CLAUDE.md and root AGENTS.md.
- Distinctive: line 9
If any instruction conflicts, use this order:
≈ “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
Cursor agent instructions: Agent Harness for WordPress
Precedence shim for the Cursor agent (IDE agent mode). Full index and domain rules: docs/AGENTS.md.
Maintenance: When stack pins, commands, or skill triggers change, update this file together with CLAUDE.md and root AGENTS.md. See docs/agents/agent-contract.md (Cross-tool parity).
Precedence
If any instruction conflicts, use this order:
docs/AGENTS.mddocs/agents/agent-contract.mddocs/agents/runtime-policy.md- Repo root
AGENTS.md(mirror / retrieval index)
Mandatory reads for Cursor agent
- Runtime context, docs index, MCP/site rules:
docs/AGENTS.md - Task shape and verification:
docs/agents/agent-contract.md - Sandbox / autonomy and risk tiers:
docs/agents/runtime-policy.md - Skills:
.claude/skills/(linked per skill from.agents/skills/)
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 | MS WordPress Abilities|1.13.0
WP-CLI|2.12.0 + ability-command 1.0.4
MCP|discover / get-ability-info / execute-ability
Ports|127.0.0.1 onlyCommon mistakes:
- Inventing ability names or parameters instead of discover → schema → execute.
- Editing infra (
docker-compose.yml,bin/,.env) for a content task. - Publishing or destructive ops without an explicit ask.
- Committing credentials or binding ports beyond loopback.
Commands (repo root)
| Task | Command |
| Provision | ./bin/setup |
| MCP URL + auth export | ./bin/connect --print |
| Health | ./bin/status |
| WP-CLI / abilities | ./bin/wp … |
| PHP debug log | ./bin/logs --debug |
| Demo content | ./bin/seed |
| Write audit log | ./bin/audit |
| Tests 0–3 | ./bin/test --skip-claude |
| Reset volumes | ./bin/reset (explicit ask only) |
./bin/connect registers Claude Code. For Cursor, use ./bin/connect --print
for the HTTP URL and Authorization header, plus skills under .claude/skills/,
or ./bin/wp for diagnostics.
Git (summary)
- Branch from
developfor day-to-day PRs; release cuts merge intomain. No agent attribution on commits or PRs. - Full contract: docs/agents/agent-contract.md.
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.