What is flint-slating CLAUDE.md?

Repository instructions for Claude Code work in the flint-slating project. They explain the project’s handbook-based workflow and require explicit approval for shared changes such as merging, releasing, or pushing protected branches.

Use them when contributing to flint-slating, especially before non-trivial work, releases, merges, or other shared-state changes.

They help an agent follow the repository’s working rules and avoid making unapproved changes to shared project state.

How ParkviewLab/flint-slating configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ParkviewLab/flint-slating. 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/ParkviewLab/flint-slating/develop/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ParkviewLab/flint-slating

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/parkviewlab/flint-slating/claude-md/github.svg)](https://agentmods.dev/instructions/parkviewlab/flint-slating/claude-md)

Your own site

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

Per session 574 This file is loaded in full into every session.

When invoked 574 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 100% copy Near-identical to another mod 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	$0.00574	$0.00574
Opus 5.5	$0.00230	$0.00230
Sonnet 5.5	$0.00115	$0.00115
Haiku 4.5	$0.00057	$0.00057

Measured 1mo ago against content hash 6aa532f8f572, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

flint-slating 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 1mo 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.

Origin

This is a copy

100% identical to ebony-enriching AGENTS.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 26 lines

How it starts

The opening of the file, as written. The whole thing — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ParkviewLab conventions

This repo follows the ParkviewLab handbook: the single source of truth for how we work. These pointer files don't re-inline its rules: read the handbook before non-trivial work, starting with ai-collaboration.md (the behavioural contract). Only the safety-critical guardrails are summarized here.

If present, read docs/northstar.md before working. It states the project's intent and is authoritative.

Shared-state writes need explicit authorization

Merging a feature PR into develop is the user's call. A broad directive ("fix all that", "finish it") authorizes work on the branch, not the merge. The back-merge pull request of a release is merged under that release's ask; nothing else is inferred from it.
Tagging, cutting a release, force-pushing, or pushing to a protected branch each need an explicit, per-action go-ahead: never inferred from a descriptive label (e.g. "→ v0.1.1"). One release ask covers the whole CLI release flow, git back-merge included: its merge of the back-merge pull request once develop's required checks have passed on the head, and the force push of its own back-merge-<tag> branch where it refreshes it.

Workflow basics

Work in an ephemeral, prefixed worktree off develop (feature-/fix-/doc-/…); don't commit on develop/main directly. Open a PR into develop.
PRs into develop are merged with a merge commit titled with the PR title and number, so the PR title carries the Conventional Commit prefix (feat:/fix:/docs:/…) the changelog is generated from.

Everything else lives in the handbook (don't rely on memory): branching, commits & changelogs, releases, Python tooling, CI, licensing, and the full communication norms; see https://github.com/ParkviewLab/handbook/tree/main/docs.

Read the full file on GitHub · 26 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.

1mo ago Changed · -16 tokens per session 6aa532f8f572
1mo ago Changed · -4 lines · +88 tokens per session 61ee066f6e65
2mo ago First seen · 30 lines · 502 tokens per session scan A 21470c25861c

Subscribe to this mod's changes

flint-slating CLAUDE.md is an instructions file published in the GitHub repository ParkviewLab/flint-slating (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 574 tokens to every session, about $0.0023 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to ebony-enriching AGENTS.md, differing in 0 lines, and is treated as a copy.

flint-slating CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
flint-slating CLAUDE.mdParkviewLab/flint-slating	Instructions file	0	1mo ago	Apache-2.0	A	574	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

flint-slating: Instructions file for Claude Code