Borrowing it
Nothing to install: this file belongs to Portwood-Global-Solutions/Portwood. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Portwood-Global-Solutions/Portwood/main/CLAUDE.mdgit clone --depth 1 https://github.com/Portwood-Global-Solutions/PortwoodWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/portwood-global-solutions/portwood/claude-md)<a href="https://agentmods.dev/instructions/portwood-global-solutions/portwood/claude-md"><img src="https://agentmods.dev/badge/instructions/portwood-global-solutions/portwood/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/portwood-global-solutions/portwood/claude-md"><img src="https://agentmods.dev/badge/instructions/portwood-global-solutions/portwood/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.09292 | $0.09292 |
| Opus 5 | $0.04646 | $0.04646 |
| Sonnet 5 | $0.01858 | $0.01858 |
| Haiku 4.5 | $0.00929 | $0.00929 |
Grade A, and why
Portwood CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Portwood
Skills
.claude/skills/ packages the project's working knowledge as Claude Code skills — they load automatically when relevant, and read as plain Markdown otherwise. Prefer them over re-deriving from this file:
| Skill | Covers |
|---|---|
dev-setup |
Fresh clone → working, tested org |
run-tests |
QA harness, e2e scripts, Apex tests, prettier, Code Analyzer |
triage-report |
Is a report a real defect or a template issue? |
fix-merge-tag |
The merge-tag resolution paths and how not to half-fix one |
html-template-authoring |
CSS 2.1 constraints, charts, fonts, images |
canvas-designer |
Canvas artboard, serializer, importer |
managed-package-rules |
global visibility, Flow Apex-Defined types, namespace traps |
How this project runs (from 2026-08-10)
Portwood is in community-development mode. Dave has deliberately stepped back from the code so contributors have work to pick up.
- File issues; don't fix them. When you find a bug, write the issue and stop. No PR, no patched working tree. The issue is the deliverable — it's the contributor work queue, so the write-up carries the weight a direct fix used to: exact repro,
file:linecitations, the mechanism proven by running the code rather than asserted, ranked fix options, an explicit scope note. Issues #282 and #295 are the reference shape. - Triage before recording. Real defect, or template-authoring problem? Most reports are template issues. See the
triage-reportskill — it's the gate, not an optional step. - Fixes happen in designated sessions only. Bugs accumulate until Dave says otherwise. Don't prompt for a release between dates.
- Only P0 jumps the queue. The test: would a customer hit this and not know their output is wrong? Silent corruption beats loud crashes.
- Reach for
good first issue/help wanted. A well-specified bug with a named fix option is exactly what a new contributor can land.community-contributioncovers the inbound side. - Community PRs change merge mechanics.
gh pr merge --adminafter self-approval was the sole-coder shortcut; real contributor PRs mean actual review, and CI gates now matter to people other than Dave —npm run format:checkblocks merge.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 215 lines · 9,292 tokens per session scan A 44f6d85b2b85
Portwood CLAUDE.md is an instructions file published in the GitHub repository Portwood-Global-Solutions/Portwood (122 stars, last pushed today), licensed Apache-2.0. It adds 9,292 tokens to every session, about $0.0465 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).