What is selvedge CLAUDE.md?

A `CLAUDE.md` instruction set for the Selvedge project, describing its documentation sources, coding rules, tests, and release checklist.

Use it when developing Selvedge so agents can check shipped features, architecture, tool definitions, versions, dependencies, and required checks.

It tells coding agents which files contain reliable project information and which conventions to follow, reducing incorrect assumptions and inconsistent changes.

How masondelan/selvedge configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to masondelan/selvedge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/masondelan/selvedge/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/masondelan/selvedge

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/masondelan/selvedge/claude-md/github.svg)](https://agentmods.dev/instructions/masondelan/selvedge/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/masondelan/selvedge/claude-md"><img src="https://agentmods.dev/badge/instructions/masondelan/selvedge/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/masondelan/selvedge/claude-md"><img src="https://agentmods.dev/badge/instructions/masondelan/selvedge/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,569 This file is loaded in full into every session.

When invoked 2,569 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.02569	$0.02569
Opus 5.5	$0.01028	$0.01028
Sonnet 5.5	$0.00514	$0.00514
Haiku 4.5	$0.00257	$0.00257

Measured 4d ago against content hash 6a95d8da48c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

selvedge 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 4d 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.

CLAUDE.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Selvedge contributor guidance

These conventions apply to everyone contributing to Selvedge, with any compatible tooling. Some clients load this filename automatically; other contributors should read it directly.

For everything else:

README.md — user-facing docs (install, quickstart, comparison, "what's new", CLI reference)
docs/architecture.md — internal architecture, data model, MCP tool reference, CLI reference, full phase plan, non-goals
CHANGELOG.md — source of truth for what's actually shipped

Sources of truth

Product values and engineering standards → docs/engineering-standards.md. Keep Selvedge easy to use, robust, developer focused and agent-agnostic across code, documentation, the website, reviews and releases. Check current primary guidance when relevant technology changes.
Community feedback and publishing review → docs/community-feedback.md. Track substantive feedback through a reasoned decision and follow-up; check released behavior before proposing features or publishing claims.
What's shipped → CHANGELOG.md. The phase-plan checkboxes in docs/architecture.md can drift; trust the changelog when they disagree.
Current MCP tool count and shape → selvedge/server.py. Don't infer from manifest.json — the bundle can lag the live server.
Version string → pyproject.toml AND selvedge/__init__.py AND manifest.json must all match.

Commit identity

Use the contributor's verified Git identity. Copy a GitHub-provided private email from that account's settings; never invent a users.noreply.github.com address from a role name. Such an address can belong to an unrelated account. Preserve legitimate contributors' authorship when importing their work.

Before creating commits, check the effective author and committer:

git var GIT_AUTHOR_IDENT
git var GIT_COMMITTER_IDENT

Read the full file on GitHub · 122 lines

Changes

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.

4d ago Changed · +34 lines · +322 tokens per session 6a95d8da48c4
5d ago Changed df4a8e14bef7
19d ago Changed · +1 lines · +132 tokens per session be22e0d6349c
1mo ago Changed · +3 lines · +191 tokens per session 7e3e3c34a343
1mo ago Changed · +3 lines · +101 tokens per session d0ee3dd25f8f
2mo ago First seen · 81 lines · 1,823 tokens per session scan A 6577713ebe95

Subscribe to this mod's changes

selvedge CLAUDE.md is an instructions file published in the GitHub repository masondelan/selvedge (26 stars, last pushed 5d ago), licensed MIT. It adds 2,569 tokens to every session, about $0.0103 per session on Opus 5.5. 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.

agent-memory agent-trace ai-agent-reasoning ai-agents ai-code-provenance ai-codebase-memory

selvedge CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
selvedge CLAUDE.mdmasondelan/selvedge	Instructions file	26	5d ago	MIT	A	2,569	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

selvedge: Instructions file for Claude Code