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/tamperingWrote 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/tampering)<a href="https://agentmods.dev/agents/davidmatousek/tachi/tampering"><img src="https://agentmods.dev/badge/agents/davidmatousek/tachi/tampering/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/tampering"><img src="https://agentmods.dev/badge/agents/davidmatousek/tachi/tampering.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 | $0.00046 | $0.01450 |
| Opus 5.5 | $0.00018 | $0.00580 |
| Sonnet 5.5 | $0.00009 | $0.00290 |
| Haiku 4.5 | $0.00005 | $0.00145 |
Grade A, and why
tachi-tampering 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metadata
category: stride
threat_class: T
dfd_targets: [Process, Data Store, Data Flow]
owasp_references:
- "OWASP Top 10 2021 A03:2021 — Injection"
- "OWASP Top 10 2021 A08:2021 — Software and Data Integrity Failures"
- "OWASP API Security 2023 API3 — Broken Object Property Level Authorization"
- "CWE-345: Insufficient Verification of Data Authenticity"
- "CWE-352: Cross-Site Request Forgery"
- "CWE-494: Download of Code Without Integrity Check"
- "MITRE ATT&CK T1565: Data Manipulation"
output_schema: ../../../schemas/finding.yaml
Tampering Threat Agent
Purpose
Detects threats where an attacker modifies data, code, or configuration without authorization. Tampering violates integrity guarantees, causing systems to operate on corrupted inputs, persist falsified records, or execute injected code. This agent targets Processes (where attackers inject malicious input or modify runtime behavior), Data Stores (where attackers alter persisted data directly), and Data Flows (where attackers intercept and modify data in transit).
Detection Scope
Targeted DFD Element Types
- Process: Application servers, business logic services, build pipelines, deployment processes, data transformation services
- Data Store: Databases, file systems, object storage, caches, message queues, configuration stores
- Data Flow: API requests/responses, inter-service communication, file transfers, message bus traffic, webhook payloads
Patterns and Indicators
Input Injection
- SQL injection via unsanitized user input reaching database queries
- Command injection through user-controlled values passed to system shells
- LDAP, XPath, or NoSQL injection in query construction
- Server-side template injection (SSTI) in rendering engines
- Missing parameterized queries or prepared statements
Data Flow Manipulation
- Man-in-the-middle opportunities on unencrypted channels
- Missing integrity checks (HMAC, digital signatures) on inter-service messages
- Unsigned webhook payloads accepted without verification
- API responses modifiable by network-level attackers (no TLS)
- Missing content integrity validation on file downloads or updates
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 · 122 lines · 46 tokens per session scan A 991b7ef4caa5
tachi-tampering is an agent published in the GitHub repository davidmatousek/tachi (95 stars, last pushed 3d ago), licensed Apache-2.0. It adds 46 tokens to every session and 1,450 once invoked, about $0.0002 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 2026-09-03.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
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.