gallformers: Instructions file for Claude Code

CLAUDE.md

gallformers CLAUDE.md is an instructions file for Claude Code from jeffdc/gallformers. It costs 1,084 tokens per session, scanned A, original, Apache-2.0.

Project-specific instructions for Gallformers, including background jobs, database setup for tests, reusable interface components, and work planning. They also define required checks before code is committed.

In plain words
What is it for?
Adding or changing Gallformers code, especially background work, database-backed tests, user-interface components, and planned tasks.
Why use it?
They give an agent the project's rules and conventions, reducing duplicate code and avoiding changes that fail the project's checks.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is jeffdc/gallformers's own configuration. It tells Claude Code how to work on gallformers 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 gallformers configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jeffdc/gallformers. 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/jeffdc/gallformers/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jeffdc/gallformers

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 gallformers CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jeffdc/gallformers/claude-md/github.svg)](https://agentmods.dev/instructions/jeffdc/gallformers/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jeffdc/gallformers/claude-md"><img src="https://agentmods.dev/badge/instructions/jeffdc/gallformers/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 gallformers CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jeffdc/gallformers/claude-md"><img src="https://agentmods.dev/badge/instructions/jeffdc/gallformers/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,084 This file is loaded in full into every session.
When invoked 1,084 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 $0.01084 $0.01084
Opus 5.5 $0.00434 $0.00434
Sonnet 5.5 $0.00217 $0.00217
Haiku 4.5 $0.00108 $0.00108

Measured 1mo ago against content hash 754bb66e5da1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gallformers 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.

CLAUDE.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRITICAL:

  • Investigation Before Action
  • Search Before You Write
  • The most common agent failure is writing new code for something that already exists. Do not do this.
  • Do not commit until precommit passes.
  • Always compile with --warnings-as-errors**. When verifying code changes, NEVER use plain mix compile - always use mix compile --warnings-as-errors or run mix precommit. CI enforces warnings-as-errors, so skipping this locally will cause CI failures.

Background Jobs

Use Oban for durable, retryable, or scheduled background work. Reserve plain GenServer loops and Process.send_after/3 for in-memory process behavior where persistence, retries, and operator visibility do not matter. The canonical queue dashboard is mounted at /admin/jobs.

Test Database

Tests use a separate PostgreSQL test database (gallformers_test) that is:

  • Schema-only: Created via Ecto migrations (no production data)
  • Minimal seed data: Loaded from priv/repo/test_seeds.sql with just enough data for tests
  • Rebuilt fresh: make test rebuilds the test DB before each run
make test-db               # Rebuild test database manually (rarely needed)

Reusable UI Components

CRITICAL: This project has reusable UI components that MUST be used. Do NOT implement custom/inline versions of these components. Creating new UI patterns requires explicit user approval.

All component files are in lib/gallformers_web/components/.

Before Adding UI Code

  1. Check existing components - Search core_components.ex and form_components.ex
  2. Check existing pages - See how similar UI is implemented elsewhere
  3. If no component exists - ASK before implementing inline. We may want to create a reusable component.

See CODING_STANDARDS.md for details as needed.

Domain Model

  • docs/domain/domain-model.md records the domain language being discovered for the redesign (galls, organisms, Sources, Observations). It is about the domain, not software, and is not yet implemented. The software design draft lives in matter 8567.
  • The current code and database follow docs/domain/general.md and docs/domain/admin-domain-reference.md ("everything is a species") until the taxonomy migration (matter 8567).
  • Don't use the target model to explain current code, or the current docs to design new work.

Read the full file on GitHub · 88 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. 1mo ago Changed · +7 lines · +157 tokens per session 754bb66e5da1
  2. 2mo ago First seen · 81 lines · 927 tokens per session scan A 747b96569dfa

Subscribe to this mod's changes

gallformers CLAUDE.md is an instructions file published in the GitHub repository jeffdc/gallformers (22 stars, last pushed today), licensed Apache-2.0. It adds 1,084 tokens to every session, about $0.0043 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.

Related

gallformers CLAUDE.md compared with instructions from other repositories

gallformers CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
gallformers CLAUDE.mdjeffdc/gallformersInstructions file22todayApache-2.0A1,084Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot