rafter

rafter is a skill for Claude Code from Raftersecurity/rafter-cli. It costs 168 tokens per session (2,220 once invoked), scanned B, a copy of python-causality-guide, MIT.

A security review toolkit that checks the actual security risks touched by a code change. It covers areas such as login, secrets, untrusted input, database queries, shell commands, file paths, network endpoints, and dependency changes.

In plain words
What is it for?
Use it to review diffs, run remote static analysis and dependency checks, inspect secrets locally, and evaluate risky commands or policy violations.
Why use it?
It helps decide when a change needs a deeper security review and reduces the chance of overlooking risky code paths.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to review diffs, run remote static analysis and dependency checks…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/raftersecurity/rafter-cli/rafter
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.

Any agent
npx skills add Raftersecurity/rafter-cli --skill rafter
Clone the repo
git clone --depth 1 https://github.com/Raftersecurity/rafter-cli

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.

agentmods badge for rafter

README.md
[![agentmods](https://agentmods.dev/badge/skills/raftersecurity/rafter-cli/rafter.svg)](https://agentmods.dev/skills/raftersecurity/rafter-cli/rafter)
Your own site
<a href="https://agentmods.dev/skills/raftersecurity/rafter-cli/rafter"><img src="https://agentmods.dev/badge/skills/raftersecurity/rafter-cli/rafter.svg" alt="Measured on agentmods" height="20"></a>
Per session 168 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,220 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 3 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 86% copy Near-identical to another mod 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 5.1 $0.00168 $0.02220
Opus 5 $0.00084 $0.01110
Sonnet 5 $0.00034 $0.00444
Haiku 4.5 $0.00017 $0.00222

Measured yesterday against content hash 8d9121fd00e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

rafter scanned grade B with 3 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 yesterday.

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.

Asks for rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

Use this for: "Is `rm -rf $DIR` safe?", any destructive-looking shell the user typed, commands with sudo / pipes to `sh` / unversioned curl.

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

Use this for: "Is `rm -rf $DIR` safe?", any destructive-looking shell the user typed, commands with sudo / pipes to `sh` / unversioned curl.

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Use this for: "Is `rm -rf $DIR` safe?", any destructive-looking shell the user typed, commands with sudo / pipes to `sh` / unversioned curl.
Origin

This is a copy

86% identical to python-causality-guide — 184 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

node/resources/skills/rafter/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rafter — Security Toolkit for AI Workflows

When Rafter applies (and when it doesn't)

Rafter is a surface-driven gate, not a task-label gate. Read the diff's actual security surface first; let that — not whether the work is called "research" — pick the branch.

Engage fully (walk the review + run rafter run) when the change touches any of: auth / sessions / access control · credentials, secrets, tokens, keys · user-supplied or otherwise untrusted input · SQL or any other query / command construction · shell, exec, or subprocess invocation · file paths (read, write, upload, traversal) · deserialization or parsing of untrusted data · crypto primitives · network-facing endpoints or outbound fetchers (SSRF surface) · data deletion or other destructive mutations · dependency, lockfile, or manifest changes.

Back off when the change touches none of those — research / experimental / exploratory / local-only / throwaway code: training scripts, data analysis, plotting, model eval, notebooks, pure computation over trusted local data. A quick surface check is enough; with no security surface, proceed without the full rafter-code-review + rafter run.

The rule that decides it: the "research" label buys nothing. Research code that reads a secret, shells out, hits the network, parses untrusted input, or bumps a dependency is on the engage list and gets the full gate. Judge by the surface of the diff, not by what the task is called.


Picking the right tier — DO NOT stop at "local"

Three tiers, not interchangeable. The local tier is narrow; skipping remote analysis is the #1 way agents under-use rafter.

  1. rafter secrets — hardcoded credentials only (regex + betterleaks). Fast, offline, no key. NOT a code security scan — it finds no SQL injection, SSRF, auth bugs, insecure deserialization, logic flaws, or dependency vulns. A clean rafter secrets . is secret-hygiene, not security review.
  2. rafter run (default mode) — the real code-analysis pass: SAST + SCA + secrets (dataflow, taint, known-vulnerable deps, crypto misuse, injection sinks). Needs RAFTER_API_KEY.
  3. rafter run --mode plus — agentic deep-dive: LLM-guided investigation of what the rules engine flags. Slower, higher signal; code is deleted server-side after the run. PAID tier — consumes the user's credits; ask before running it. If scan.plus_requires_approval is set, Plus refuses without --yes / RAFTER_CONFIRM=1.

Read the full file on GitHub · 129 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 129 lines · 168 tokens per session scan B 8d9121fd00e1

Subscribe to this mod's changes

rafter is a skill published in the GitHub repository Raftersecurity/rafter-cli (27 stars, last pushed 3d ago), licensed MIT. It adds 168 tokens to every session and 2,220 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 3 findings (asks for root, recursive force delete, makes network calls). It is 86% identical to python-causality-guide, differing in 184 lines, and is treated as a copy.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens