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/norvialabs/forge/claude-mdgit clone --depth 1 https://github.com/NorviaLabs/forgeWrote 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/norvialabs/forge/claude-md)<a href="https://agentmods.dev/instructions/norvialabs/forge/claude-md"><img src="https://agentmods.dev/badge/instructions/norvialabs/forge/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 | $0.00331 | $0.00331 |
| Opus 5 | $0.00166 | $0.00166 |
| Sonnet 5 | $0.00066 | $0.00066 |
| Haiku 4.5 | $0.00033 | $0.00033 |
Grade A, and why
forge 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 3d 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.
What it actually says
Verification
When asked to test TUI behavior interactively, do the PTY/tmux driving yourself — do NOT delegate interactive testing to a background subagent. Subagents may be used for parallel capture/build work only.
Answering questions about behavior
If asked 'is X bound / does Y exist / what does Z do', read the source first. Only launch a PTY/tmux run when the question is about observable runtime rendering that code reading cannot settle.
Build & Test
Editing rules
Never use sed/regex/line-range deletions for multi-line Rust code. Use the Edit tool with exact anchored strings, one edit per site. Blanket renames must be scoped to the target crate and reviewed file-by-file.
Definition of done
Every code change ships with: (1) a new or updated test covering the change, (2) cargo fmt --all, (3) cargo clippy --all-targets, (4) cargo test --workspace green — before opening a PR.
Git & GitHub workflow
Issue and PR references
'Fix #N' means: first run gh pr view N and gh issue view N to determine whether N is an issue or an existing PR. If a PR already exists for the work, fix that branch — never reimplement on main.
UI / TUI
TUI layout conventions
Columnar TUI content uses ratatui Table, never hand-padded List strings. Hints and secondary context are right-aligned per forge convention. Do not add navigation hints unless explicitly requested.
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.
- 3d ago First seen · 30 lines · 331 tokens per session scan A 1dc86006f998
forge CLAUDE.md is an instructions file published in the GitHub repository NorviaLabs/forge (5 stars, last pushed 3d ago), licensed MIT. It adds 331 tokens to every session, about $0.0017 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.
Other instructions, from other repositories
jcode AGENTS.md
AGENTS.md instructions for 1jehuang/jcode, covering repository guidelines, development workflow, install notes and verifying a change at runtime.
autolith AGENTS.md
AGENTS.md instructions for lambda-symbolics/autolith, covering repository guidelines, purpose and sources of truth, upstream references, architectural guardrails and package policy.
senpi AGENTS.md
AGENTS.md instructions for code-yeongyu/senpi, covering senpi repository guide, mandatory execution protocols — non-negotiable, protocol 1 — explicitly requested modifications, protocol 2 — user-requested pr reviews and structure.
Albatross AGENTS.md
Instructions for morganlinton/Albatross, covering agent instructions, general and releases.
Xenon CLAUDE.md
Instructions for xianyu-sheng/Xenon, covering claude.md — xenon 项目规范, bug 修复原则, 深度根因分析，而非逐洞补漏, 通用设计，而非特例枚举 and 每次新增 mcp 工具都要加正则 — 不可持续.
x-code-cli AGENTS.md
Instructions for woai3c/x-code-cli, covering agents.md, rules, commands, delivery workflow and architecture.