agentmods.dev

dev-pack CLAUDE.md

A set of Claude Code instructions for developing the dev-pack itself, a collection of rules, skills, hooks, commands, agents, and templates for Next.js and Supabase projects.

In plain words
What is it for?
Use it when adding or changing pack components, testing hooks, checking configuration, or updating the inventory and changelog.
Why use it?
It gives contributors clear project rules and checks, so changes to the pack are tested, documented, and kept accurate.

Instructions file

2 2mo ago A scan 364 tokens original MIT
View the source file m-binimran/dev-pack
Install

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.

agentmods
npx agentmods add instructions/m-binimran/dev-pack/claude-md
Clone the repo
git clone --depth 1 https://github.com/m-binimran/dev-pack
Per session 364 This file is loaded in full into every session.
When invoked 364 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00364 $0.00364
Opus 5 $0.00182 $0.00182
Sonnet 5 $0.00073 $0.00073
Haiku 4.5 $0.00036 $0.00036

Measured 2d ago against content hash 192117bebded, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-pack 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 2d 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 · 28 lines

What it actually says

CLAUDE.md — working ON dev-pack

This is the repo for the pack itself. (For using the pack in your project, run an installer — see README.)

What this repo is

A curated, enforced Claude Code pack for database + website builders on Next.js + Supabase. Layers: rules/ (advisory) · skills/ (on-demand) · hooks/ (deterministic) · loops/ (slash commands) · agents/ (subagents) · mcp/ · templates/. Full list in INVENTORY.md.

House rules for changing this repo

  • Every item must serve a stated goal: fewer tokens, accuracy, truth-telling, speed, quality.
  • Hooks must be tested. Add a case to tests/test_hooks.py and run it: python tests/test_hooks.py. State the fail mode (open/closed) in the hook docstring.
  • Keep rule/skill files short — they cost tokens every turn.
  • No inflated claims anywhere. Anything documented as working must actually have been run. This repo practices the truth-telling it preaches.
  • Update INVENTORY.md and CHANGELOG.md when adding/removing items.

Verify

python tests/test_hooks.py        # all hook behavior
python -c "import json;json.load(open('hooks/settings.json'))"   # config valid

Conventions

  • Commit format: <type>: <description> (feat/fix/docs/refactor/test/chore).
  • Hooks are Python 3.8+ (cross-platform). One logical change per PR.
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. 2d ago First seen · 28 lines · 364 tokens per session scan A 192117bebded

Subscribe to this mod's changes

dev-pack CLAUDE.md is an instructions file published in the GitHub repository m-binimran/dev-pack (2 stars, last pushed 2mo ago), licensed MIT. It adds 364 tokens to every session, about $0.0018 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 2026-08-31.

Building agentsGuardrailsagent-skillsai-agentsclaudeclaude-codedeveloper-tools
Related

Other instructions, from other repositories

Doberman-Core AGENTS.md

Instructions for DobermanCore/Doberman-Core, covering claude.md — doberman operating manual, 0. on startup (every session), 1. what this repository is, 2. architecture & extension points and 3. prime directives (non-negotiable).

DobermanCore/Doberman-Core · 3,547 tokens

agent-guardrails-template copilot-instructions.md

Instructions for TheArchitectit/agent-guardrails-template, covering github copilot instructions, the four laws of agent safety, code generation rules, scope (mandatory) and production-first.

TheArchitectit/agent-guardrails-template · 852 tokens

vibeguard AGENTS.md

Instructions for majiayu000/vibeguard, covering agent instructions, scope, start here, core rules and delivery policy.

majiayu000/vibeguard · 1,335 tokens

Guardrails CLAUDE.md

Claude Code instructions for NVIDIA-NeMo/Guardrails, a project described as: NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

NVIDIA-NeMo/Guardrails · 3 tokens

plan-forge aci-design.instructions.md

Agent-Computer Interface (ACI) rules — how every forge MCP tool must shape its inputs and outputs so the calling agent can use it reliably. Auto-loads when editing tool definitions or capabilities.

srnichols/plan-forge · 2,072 tokens

plan-forge self-repair-reporting.instructions.md

Self-repair reporting — when and how to file meta-bugs against Plan Forge itself using forgemetabugfile.

srnichols/plan-forge · 1,327 tokens