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/d4rkninja/arcforge/claude-mdgit clone --depth 1 https://github.com/d4rkNinja/arcforgeWrote 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/d4rkninja/arcforge/claude-md)<a href="https://agentmods.dev/instructions/d4rkninja/arcforge/claude-md"><img src="https://agentmods.dev/badge/instructions/d4rkninja/arcforge/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 | $0.00691 | $0.00691 |
| Opus 5 | $0.00345 | $0.00345 |
| Sonnet 5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
arcforge 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 today.
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.
What it actually says
Claude Code Repository Instructions
Read AGENTS.md as the repository source of truth.
This is a portable Agent Skills repository. Keep all eighteen skills runtime-neutral and do not add native Claude Code plugins, hooks, agents, or a separate harness configuration unless the user explicitly requests a new distribution format.
Route work by skill:
Routing layer (use when the owning skill, the mode, or the order is not settled):
- pick the skill, the mode, the companions, and the order, then continue into the work ->
skills/using-forge/SKILL.md; - answer which skill, which mode, and what order, then stop, with nothing inspected or changed ->
skills/think-forge/SKILL.md.
Architecture layer:
- general system design ->
skills/system-architecture-harness/SKILL.md; - LLM, RAG, memory, tools, or agents ->
skills/ai-agent-system-architecture/SKILL.md; - architecture review or approval ->
skills/architecture-review-gate/SKILL.md. - concrete pull request, merge request, commit range, patch, or repository-diff review with findings, fixes, false-positive disposition, verdict, and instruction-derived score ->
skills/pull-request-review-gate/SKILL.md.
Domain thinking layer (select think, review, change, or verify and read the routed papers before making claims):
- identity, authentication, sessions, permissions, tenancy ->
skills/auth-access/SKILL.md; - APIs, validation, errors, pagination, versioning, webhooks, realtime, SDKs ->
skills/api-contracts/SKILL.md; - schemas, identifiers, money, time, indexes, files, search, lifecycle ->
skills/data-storage/SKILL.md; - transactions, locking, idempotency, sagas, sharding, distributed locks ->
skills/transactions-consistency/SKILL.md; - jobs, queues, events, outbox, batch, email, notifications ->
skills/async-messaging/SKILL.md; - caching, rate limiting, quotas, retries, timeouts, breakers, backpressure ->
skills/resilience-flow-control/SKILL.md; - secrets, crypto, TLS, sensitive data, redaction, abuse, randomness ->
skills/security-privacy/SKILL.md; - logging, metrics, tracing, health, audit, runbooks, backup/DR, multi-region ->
skills/production-operations/SKILL.md; - schema/data/contract migration, backfills, cutover, legacy integration ->
skills/migration-evolution/SKILL.md; - test strategy, concurrency/failure/load evidence, release checklist ->
skills/quality-release/SKILL.md; - config, connection pools, graceful shutdown, deploy ordering, CI/CD ->
skills/runtime-delivery/SKILL.md; - branches, commits, merges, rebases, remotes, tags, versions, protected refs, history rewrites, Git recovery ->
skills/git-workflows/SKILL.md.
Domain papers live in each skill's references/papers/. When a canonical paper
changes, update every owning skill copy with it and review semantic parity and
links; do not hand-edit only one side.
Use the Skills CLI for installation checks and restart Claude Code when a newly created top-level skill directory is not visible in the current session.
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.
- today Changed · +1 lines · +47 tokens per session 4804da3a5302
- 4d ago First seen · 41 lines · 644 tokens per session scan A 1a48b6e66092
arcforge CLAUDE.md is an instructions file published in the GitHub repository d4rkNinja/arcforge (16 stars, last pushed yesterday), licensed MIT. It adds 691 tokens to every session, about $0.0035 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
mcp-adr-analysis-server copilot-instructions.md
Copilot instructions for tosin2013/mcp-adr-analysis-server, covering mcp adr analysis server - ai coding agent instructions, project overview, critical technical conventions, esm-only module system and typescript configuration.
symphony AGENTS.md
Instructions for broomva/symphony, covering agents.md - symphony, repository purpose, architecture, key design decisions and gathering context from the knowledge graph.
cosmos-os CLAUDE.md
Instructions for ludeo-labs/cosmos-os, covering the cosmos — notes for claude code, commands, layout and invariants.
claude-proj-blueprint CLAUDE.md
Instructions for rtazima/claude-proj-blueprint, covering project, tech stack, architecture, documentation directories and code conventions.
ai-software-architect AGENTS.md
AGENTS.md instructions for codenamev/ai-software-architect, covering agents.md - ai software architect framework, project overview, framework development setup, repository structure and installation for framework development.
intentflow-ios intentflow-swift.instructions.md
Instructions for emrecanozturk/intentflow-ios, a project described as: Workflow-first, AI-ready iOS architecture with typed effects, manifests, SwiftUI/UIKit examples, and agent-safe code generation.