tachi-spoofing

tachi-spoofing is an agent for Claude Code from davidmatousek/tachi. It costs 42 tokens per session (1,256 once invoked), scanned A, original, Apache-2.0.

A security analysis agent that looks for ways attackers could pretend to be legitimate users, services, or system components.

In plain words
What is it for?
It reviews threat models for authentication bypasses, forged service identities, and other impersonation risks.
Why use it?
It helps uncover authentication weaknesses such as stolen credentials, session hijacking, and identity-provider attacks before they are abused.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is output_schema: ../../../schemas/finding.yaml.

Good fit It reviews threat models for authentication bypasses, forged service identities, and other impersonation risks.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/davidmatousek/tachi
agentmods
npx agentmods add agents/davidmatousek/tachi/spoofing

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 tachi-spoofing

README.md
[![agentmods](https://agentmods.dev/badge/agents/davidmatousek/tachi/spoofing/github.svg)](https://agentmods.dev/agents/davidmatousek/tachi/spoofing)
Your own site
<a href="https://agentmods.dev/agents/davidmatousek/tachi/spoofing"><img src="https://agentmods.dev/badge/agents/davidmatousek/tachi/spoofing/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.

agentmods 80×15 button for tachi-spoofing

Your own site · 80×15
<a href="https://agentmods.dev/agents/davidmatousek/tachi/spoofing"><img src="https://agentmods.dev/badge/agents/davidmatousek/tachi/spoofing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,256 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00042 $0.01256
Opus 5 $0.00021 $0.00628
Sonnet 5 $0.00008 $0.00251
Haiku 4.5 $0.00004 $0.00126

Measured 6d ago against content hash e175fcdfabae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tachi-spoofing 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 6d 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.

adapters/claude-code/agents/spoofing.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Metadata

category: stride
threat_class: S
dfd_targets: [External Entity, Process]
owasp_references:
  - "OWASP Top 10 2021 A07:2021 — Identification and Authentication Failures"
  - "OWASP API Security 2023 API2 — Broken Authentication"
  - "CWE-287: Improper Authentication"
  - "CWE-290: Authentication Bypass by Spoofing"
  - "CWE-384: Session Fixation"
  - "MITRE ATT&CK T1078: Valid Accounts"
  - "MITRE ATT&CK T1556: Modify Authentication Process"
output_schema: ../../../schemas/finding.yaml

Spoofing Threat Agent

Purpose

Detects threats where an attacker assumes the identity of another entity — user, service, or system component. Spoofing undermines authentication guarantees, enabling an adversary to perform actions under a trusted identity. This agent targets External Entities (where attackers impersonate legitimate users or upstream systems) and Processes (where attackers forge inter-service identity to bypass trust assumptions).

Detection Scope

Targeted DFD Element Types

  • External Entity: Users, API clients, upstream services, third-party integrations, federated identity providers
  • Process: Backend services, microservices, API gateways, authentication middleware, token issuers

Patterns and Indicators

Authentication Bypass

  • Missing or weak authentication on entry points (no MFA, password-only)
  • Default or hard-coded credentials in service accounts
  • Authentication decisions made client-side without server validation
  • Missing mutual TLS between services in zero-trust boundaries

Credential Theft and Replay

  • Tokens transmitted over unencrypted channels (HTTP instead of HTTPS)
  • Long-lived tokens without rotation or revocation mechanisms
  • Credentials stored in plaintext or weakly hashed (MD5, SHA-1 without salt)
  • Bearer tokens without audience or issuer validation

Session Hijacking

  • Session identifiers predictable or sequentially generated
  • Session tokens exposed in URLs, logs, or error messages
  • Missing session binding to client fingerprint (IP, user-agent)
  • No session invalidation on privilege changes (login, role change)

Read the full file on GitHub · 109 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. 6d ago First seen · 109 lines · 42 tokens per session scan A e175fcdfabae

Subscribe to this mod's changes

tachi-spoofing is an agent published in the GitHub repository davidmatousek/tachi (91 stars, last pushed 28d ago), licensed Apache-2.0. It adds 42 tokens to every session and 1,256 once invoked, about $0.0002 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 2026-09-03.