What is sam CLAUDE.md?

Instructions for sam-agents, an npm command-line tool that installs agent definitions and platform-specific skills into projects. It describes the project layout, supported platforms, workflows, commands, and synchronization rules.

Use it when editing sam-agents agents, workflows, manifests, platform generators, or templates. It also covers verification scripts and commands for checking synchronization and manifests.

It explains how to maintain sam-agents safely, including which files are the source of truth and how generated templates must stay synchronized.

How sam-agents/sam configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to sam-agents/sam. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/sam-agents/sam/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/sam-agents/sam

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/sam-agents/sam/claude-md/github.svg)](https://agentmods.dev/instructions/sam-agents/sam/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/sam-agents/sam/claude-md"><img src="https://agentmods.dev/badge/instructions/sam-agents/sam/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/sam-agents/sam/claude-md"><img src="https://agentmods.dev/badge/instructions/sam-agents/sam/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 911 This file is loaded in full into every session.

When invoked 911 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00911	$0.00911
Opus 5.5	$0.00364	$0.00364
Sonnet 5.5	$0.00182	$0.00182
Haiku 4.5	$0.00091	$0.00091

Measured 1mo ago against content hash f55312b2e046, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sam 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 1mo 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 · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SAM (sam-agents)

Autonomous TDD agent system distributed as an npm CLI. Installs agent definitions and per-platform skills into target projects (Claude Code, Cursor, Gemini CLI, GitHub Copilot, Antigravity).

This is a template-generation tool, not a runtime app — there are no unit tests, only verification scripts.

Layout

bin/cli.js              # CLI entry point — install logic + per-platform generators
_sam/                   # Source of truth: agent definitions + workflows
  agents/               # Individual agent configs (architect, dev, reviewer, test, etc.)
  core/workflows/       # Autonomous TDD pipeline (step-01 … step-04)
  _config/              # Manifests (agent-manifest.csv, manifest.yaml)
  docs/                 # Per-platform guides (GEMINI, COPILOT, DEPLOYMENT)
templates/_sam/         # Mirror of _sam/ — what gets shipped to consumers
templates/.claude/      # Claude Code command wrappers
scripts/                # sync-templates, verify-sync, verify-manifest, verify-gemini

The `_sam/` ↔ `templates/_sam/` rule

_sam/ is the single source of truth. templates/_sam/ is a generated mirror that ships in the npm package.

Edit _sam/ only, then run npm run sync-templates before committing.
npm test runs verify-sync.js and will fail CI if they drift.
Never hand-edit templates/_sam/.

Commands

npm test                  # verify-manifest + verify-sync + verify-gemini
npm run sync-templates    # _sam/ → templates/_sam/
node bin/cli.js --platform all ./test-project   # manual smoke test

Adding or editing an agent

Edit (or create) the markdown file under _sam/agents/.
If new: add a row to _sam/_config/agent-manifest.csv and register it in the platform agent lists in bin/cli.js (generateCursorRules, generateAntigravitySkills, generateGeminiSkills).
Run npm run sync-templates, then npm test.
Smoke-test with node bin/cli.js --platform all ./test-project.

Agent file format

Read the full file on GitHub · 74 lines

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.

1mo ago First seen · 74 lines · 911 tokens per session scan A f55312b2e046

Subscribe to this mod's changes

sam CLAUDE.md is an instructions file published in the GitHub repository sam-agents/sam (19 stars, last pushed 3mo ago), licensed MIT. It adds 911 tokens to every session, about $0.0036 per session on Opus 5.5. 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.

Building agents Claude Code Code Generation agents ai-agents antigravity autonomous-coding

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).

microsoft/vscode · 9,715 tokens

sam: Instructions file for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

SAM (sam-agents)

Layout

The `_sam/` ↔ `templates/_sam/` rule

Commands

Adding or editing an agent

Agent file format

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

next.js AGENTS.md

vscode oss-third-party-notices.instructions.md

langchain AGENTS.md

vscode copilot-instructions.md

deepseek-harness AGENTS.md

sam: Instructions file for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

SAM (sam-agents)

Layout

The _sam/ ↔ templates/_sam/ rule

Commands

Adding or editing an agent

Agent file format

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

next.js AGENTS.md

vscode oss-third-party-notices.instructions.md

langchain AGENTS.md

vscode copilot-instructions.md

deepseek-harness AGENTS.md

The `_sam/` ↔ `templates/_sam/` rule