ImYourBoyRoyImYourBoyRoy/Portable_Web_toolkit/Web_Toolkit/AGENTS.md

Portable_Web_toolkit / Web_Toolkit

AGENTS.md2 starsChanged 4 months agoMITView on GitHub

Canonical copy: see ../AGENTS.md at the repo root. When this directory is linked into a client project, the client repository's applicable instructions govern site work. This file governs toolkit source and does not override client safety or release policy. Infrastructure: audit → dry-run → --apply. Full sequence: OPERATIONS.md. The versioned source is ../skill-pack.json. From the repository root, node ./scripts/check-agent-skills.mjs --agent <client> reports status without changing files. An authorized installation follows ../docs/agent-skills/INSTALL_PROTOCOL.md; the helper is not an installer. The master router…

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 repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- brand-doctorSkill
- discovery-doctorSkill
- image-pipelineSkill
- instagram-cloneSkill
- pagespeed-diagnosticsSkill
- portable-web-toolkit-routerSkill
- portable-web-toolkitSkill
- site-maintenanceSkill
- site-onboardingSkill
- site-readinessSkill
- site-starterSkill
- toolkit-updateSkill
- vectorize-pipelineSkill
- wcag-auditorSkill

The file

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

1 rule. About 0 are common, 1 is distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
When this directory is linked into a client project, the client repository's applicable instructions govern site work.
line 12

≈ “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

Portable Web Toolkit — Agent Instructions (Web_Toolkit)

Canonical copy: see ../AGENTS.md at the repo root.

Do first

../START_HERE.md
README.md
OPERATIONS.md (reference — primary path is site-readiness JSON)
ARCHITECTURE.md

When this directory is linked into a client project, the client repository's applicable instructions govern site work. This file governs toolkit source and does not override client safety or release policy.

What matters most

site-profiles/*.json (or --site-profile path) drives all tools
Target project root .env for live secrets — not toolkit .env
Generated artifacts in .runtime/ only
Dry-run before --apply on Cloudflare, DNS, cache, registrar
Custom discovery generators — not @astrojs/sitemap / @astrojs/robots
discovery-doctor is standards-aware and policy-driven: the default contract requires llms*, API, humans, and security resources; explicitly relaxed or runtime-only resources are INFO when absent, while advertised-but-invalid resources are FAIL. Put client-specific requirements under diagnostics.discovery in the site profile.
Live MCP discovery is read-only: probe modern 2026-07-28 server/discover/list methods with legacy fallback; never call tools or attach credentials. Local SSR/MCP routes are runtime-only evidence and require a live check.
security.txt is required for production by default; development, preview, and staging policies may omit it because the generator intentionally returns 404 on non-indexable hosts.
site-readiness run before material work when current evidence is absent or stale
Automatic freshness runs at most once per 24 hours. It may fast-forward only a clean public main checkout; it never overwrites dirty, feature, exported, or unmanaged state. WCAGate refresh follows the public GitHub main head.

Site deploy gate

site-readiness run → read JSON report
npm run check → npm run build
discovery-doctor on ./dist
Staging → smoke → production → live discovery
Sync client MEMORY.md + Brand Guide if identity changed

Infrastructure: audit → dry-run → --apply. Full sequence: OPERATIONS.md.

Skills

The versioned source is ../skill-pack.json. From the repository root, node ./scripts/check-agent-skills.mjs --agent <client> reports status without changing files. An authorized installation follows ../docs/agent-skills/INSTALL_PROTOCOL.md; the helper is not an installer. The master router is portable-web-toolkit.

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