agentmods.dev

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.

In plain words
What is it for?
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.
Why use it?
It explains how to maintain sam-agents safely, including which files are the source of truth and how generated templates must stay synchronized.

Instructions file

18 1mo ago A scan 911 tokens original MIT
View the source file sam-agents/sam
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/sam-agents/sam/claude-md
Clone the repo
git clone --depth 1 https://github.com/sam-agents/sam
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. 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 $0.00911 $0.00911
Opus 5 $0.00456 $0.00456
Sonnet 5 $0.00182 $0.00182
Haiku 4.5 $0.00091 $0.00091

Measured 2d ago against content hash f55312b2e046, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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 · 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

  1. Edit (or create) the markdown file under _sam/agents/.
  2. 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).
  3. Run npm run sync-templates, then npm test.
  4. 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.

  1. 2d 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 (18 stars, last pushed 1mo ago), licensed MIT. It adds 911 tokens to every session, about $0.0046 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.

Building agentsCode Generationagentsai-agentsantigravityautonomous-codingclaude-code
Related

Other instructions, from other repositories

aiworkspace AGENTS.md

Instructions for a-tokyo/aiworkspace, covering ai workspace, structure, key commands, conventions and code quality.

a-tokyo/aiworkspace · 388 tokens

skills AGENTS.md

AGENTS.md instructions for Apolinariolanga/skills, covering agents.md, project overview, commands, architecture and update checking system.

Apolinariolanga/skills · 955 tokens

agent-skills AGENTS.md

Instructions for LLl0k0laD/agent-skills, covering agents.md, repository overview, creating a new skill, directory structure and naming conventions.

LLl0k0laD/agent-skills · 750 tokens

P0G AGENTS.md

Instructions for yz9yt/P0G, covering p0g agent guidelines, core principles, 1. clean instance mindset, 2. explicit over implicit and 3. minimal footprint.

yz9yt/P0G · 3,409 tokens

research-os AGENTS.md

Instructions for lxinfei5/research-os, covering researchos — constitution, §0 what this is, §1 directory discipline, §2 half-life (innovation 1) — memory design and §3 behavior pillars (innovations 2–5).

lxinfei5/research-os · 1,143 tokens

agentic-workflow CLAUDE.md

Instructions for gtrabanco/agentic-workflow, covering claude.md, repository layout, working rules, authoring a skill and hand off, don't compose across a model/effort boundary.

gtrabanco/agentic-workflow · 4,297 tokens