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/suiflex/forgeguard/claude-mdgit clone --depth 1 https://github.com/suiflex/ForgeGuardWrote 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/suiflex/forgeguard/claude-md)<a href="https://agentmods.dev/instructions/suiflex/forgeguard/claude-md"><img src="https://agentmods.dev/badge/instructions/suiflex/forgeguard/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 | $0.00418 | $0.00418 |
| Opus 5 | $0.00209 | $0.00209 |
| Sonnet 5 | $0.00084 | $0.00084 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
ForgeGuard 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 5d 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
ForgeGuard
For code changes, use /forgeguard-engineering.
Working in this repository
- Do not run
forgeguard initagainst the repository root. ForgeGuard installs into its own checkout like any other project, writing.claude/settings.json,.claude/skills/, and.forgeguard/. Usesh tests/sandbox.shto build throwaway repositories under the gitignoredsandbox/instead. AGENTS.mdis a symlink toCLAUDE.md; editCLAUDE.md.
Checks
.github/workflows/ci.yml runs, in order:
cargo fmt --all -- --check
cargo clippy --workspace --all-targets --all-features -- -D warnings
cargo test --locked --workspace
cargo build --locked --workspace --release
sh tests/install_test.sh
sh tests/wizard_test.sh
tests/wizard_test.sh drives the interactive init wizard through a
pseudo-terminal, so it needs a built binary and takes the first of
target/debug or target/release. sh tests/logo.sh --check verifies the
banner grid still matches assets/brand/logo-mark.svg; it is not part of CI
because it needs macOS qlmanage and Pillow.
Things that have bitten before
- The Windows release job only builds, so test code that fails to compile there
is never caught by CI. Gate unix-only tests with
#[cfg(unix)]. - A
// forgeguard: allow FG-XXX -- reasonmarker suppresses the rule for only the two lines that follow it, so keep the marker on the line above the finding. - Terminal output uses the stdlib-only
thememodule incrates/forgeguard-cli/src/main.rs— no color crates. Anything it prints must collapse to plain text when stdout is not a terminal orNO_COLORis set.
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.
- 5d ago First seen · 41 lines · 418 tokens per session scan A 8e9ea32e6022
ForgeGuard CLAUDE.md is an instructions file published in the GitHub repository suiflex/ForgeGuard (14 stars, last pushed today), licensed MIT. It adds 418 tokens to every session, about $0.0021 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.
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.