Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/jeffdc/gallformers/claude-mdgit clone --depth 1 https://github.com/jeffdc/gallformersWrote 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/jeffdc/gallformers/claude-md)<a href="https://agentmods.dev/instructions/jeffdc/gallformers/claude-md"><img src="https://agentmods.dev/badge/instructions/jeffdc/gallformers/claude-md.svg" alt="Measured on agentmods" 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 | $0.00927 | $0.00927 |
| Opus 5 | $0.00464 | $0.00464 |
| Sonnet 5 | $0.00185 | $0.00185 |
| Haiku 4.5 | $0.00093 | $0.00093 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 81 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 plainmix compile- always usemix compile --warnings-as-errorsor runmix 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.sqlwith just enough data for tests - Rebuilt fresh:
make testrebuilds 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
- Check existing components - Search
core_components.exandform_components.ex - Check existing pages - See how similar UI is implemented elsewhere
- If no component exists - ASK before implementing inline. We may want to create a reusable component.
See CODING_STANDARDS.md for details as needed.
Work Tracking & Planning
Mull is the single source of truth
All work tracking — ideas, plans, research, status — lives in mull matters. There are no separate plan documents committed to git.
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 First seen · 81 lines · 927 tokens per session scan A 747b96569dfa
gallformers CLAUDE.md is an instructions file published in the GitHub repository jeffdc/gallformers (22 stars, last pushed 2d ago), licensed Apache-2.0. It adds 927 tokens to every session, about $0.0046 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
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.