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.
git clone --depth 1 https://github.com/davidmatousek/tachinpx agentmods add agents/davidmatousek/tachi/spoofingWrote 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/agents/davidmatousek/tachi/spoofing)<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.
<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>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 | $0.00042 | $0.01256 |
| Opus 5 | $0.00021 | $0.00628 |
| Sonnet 5 | $0.00008 | $0.00251 |
| Haiku 4.5 | $0.00004 | $0.00126 |
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.
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)
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.
- 6d ago First seen · 109 lines · 42 tokens per session scan A e175fcdfabae
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.