planday-bridge: Instructions file for Claude Code

CLAUDE.md

planday-bridge CLAUDE.md is an instructions file for Claude Code from MVPR-Ext-Projects/planday-bridge. It costs 1,398 tokens per session, scanned A, original, MIT.

Repository instructions for using Claude Code with the Planday workforce-management integration. They explain setup, project context, and how to work with Planday data and code.

In plain words
What is it for?
Installing dependencies, testing the bridge with dummy data, configuring Planday access, and navigating the project while following its canonical instructions.
Why use it?
They give an agent a safe setup sequence and make clear which credentials the user must obtain themselves.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code; mentions AGENTS.md.

This is MVPR-Ext-Projects/planday-bridge's own configuration. It tells Claude Code how to work on planday-bridge itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything planday-bridge configures →

Reuse

Borrowing it

Nothing to install: this file belongs to MVPR-Ext-Projects/planday-bridge. 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/MVPR-Ext-Projects/planday-bridge/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/MVPR-Ext-Projects/planday-bridge

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.

agentmods badge for planday-bridge CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mvpr-ext-projects/planday-bridge/claude-md/github.svg)](https://agentmods.dev/instructions/mvpr-ext-projects/planday-bridge/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mvpr-ext-projects/planday-bridge/claude-md"><img src="https://agentmods.dev/badge/instructions/mvpr-ext-projects/planday-bridge/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.

agentmods 80×15 button for planday-bridge CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mvpr-ext-projects/planday-bridge/claude-md"><img src="https://agentmods.dev/badge/instructions/mvpr-ext-projects/planday-bridge/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,398 This file is loaded in full into every session.
When invoked 1,398 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01398 $0.01398
Opus 5.5 $0.00559 $0.00559
Sonnet 5.5 $0.00280 $0.00280
Haiku 4.5 $0.00140 $0.00140

Measured 2mo ago against content hash 3fc68641cc24, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

planday-bridge 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 2mo 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 · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

planday-bridge

AGENTS.md is the canonical context file — architecture, the traps, and the rules that must not be weakened. Read it before changing anything.

Setting this up for someone (agent playbook)

If a user has just arrived here and asked you to get it working, this is the sequence. Most of it you can do; two steps you cannot, and should hand back.

Prerequisites: Node 20 or newer. pnpm is what the lockfile is for, but npm install works fine — check which is available rather than assuming.

Step 1 — prove it runs locally, before any credentials.

pnpm install && pnpm dummy     # or: npm install && npm run dummy

Expect a table and ~626 rows of sample data. If that works, the whole pipeline works and anything that fails later is configuration, not code.

Step 2 — the user must fetch their own Planday credentials. You cannot.

It needs an admin login to their Planday portal in a browser. Ask them to go to Settings → Integrations → API Access → Create App, tick the scopes listed in SETUP.md, click Authorise, and copy the Client ID and Refresh Token.

Do not ask them to paste those values into the chat. A Planday refresh token grants access to staff and payroll data and does not expire on its own. Instead, create the file for them and have them fill it in:

cp .env.example .env && open -e .env    # or: code .env

Then run pnpm doctor. It checks environment, configuration, connection, every Planday scope separately, and a real report build, reporting each layer in order - fix the first FAIL, since later checks depend on earlier ones. Its output contains no credentials or staff data, so it is safe to quote back to the user or paste into an issue. Read the output, never the token.

Step 3 — deploy. You can drive this, but the secrets step is theirs.

The README has a one-click Vercel button, which is the better route for a non-technical user. From a terminal:

npm i -g vercel
vercel login
vercel link                                    # creates the project

# Ask the user to run these three themselves and type the values at the prompt,
# so the secrets never enter this transcript or their shell history.
vercel env add PLANDAY_CLIENT_ID production
vercel env add PLANDAY_REFRESH_TOKEN production
vercel env add BRIDGE_KEY production           # any long random password they choose

vercel deploy --prod

Read the full file on GitHub · 132 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.

  1. 2mo ago First seen · 132 lines · 1,398 tokens per session scan A 3fc68641cc24

Subscribe to this mod's changes

planday-bridge CLAUDE.md is an instructions file published in the GitHub repository MVPR-Ext-Projects/planday-bridge (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,398 tokens to every session, about $0.0056 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 2026-08-31.

Related

planday-bridge CLAUDE.md compared with instructions from other repositories

planday-bridge CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
planday-bridge CLAUDE.mdMVPR-Ext-Projects/planday-bridgeInstructions file02mo agoMITA1,398Claude Code
mcp-server-excel copilot-instructions.mdsbroenne/mcp-server-excelInstructions file853yesterdayMITA107GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot