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/denial-of-serviceWrote 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/denial-of-service)<a href="https://agentmods.dev/agents/davidmatousek/tachi/denial-of-service"><img src="https://agentmods.dev/badge/agents/davidmatousek/tachi/denial-of-service/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/denial-of-service"><img src="https://agentmods.dev/badge/agents/davidmatousek/tachi/denial-of-service.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 | $0.00048 | $0.01662 |
| Opus 5 | $0.00024 | $0.00831 |
| Sonnet 5 | $0.00010 | $0.00332 |
| Haiku 4.5 | $0.00005 | $0.00166 |
Grade A, and why
tachi-denial-of-service 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 8d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metadata
category: stride
threat_class: D
dfd_targets: [Process, Data Store, Data Flow]
owasp_references:
- "OWASP Application Denial of Service Cheat Sheet"
- "OWASP API Security 2023 API4 — Unrestricted Resource Consumption"
- "CWE-400: Uncontrolled Resource Consumption"
- "CWE-770: Allocation of Resources Without Limits or Throttling"
- "CWE-502: Deserialization of Untrusted Data"
- "MITRE ATT&CK T1498: Network Denial of Service"
- "MITRE ATT&CK T1499: Endpoint Denial of Service"
output_schema: ../../../schemas/finding.yaml
Denial of Service Threat Agent
Purpose
Detects threats where an attacker degrades or eliminates system availability — through resource exhaustion, flooding, algorithmic complexity exploitation, or cascading dependency failures. Denial of service undermines availability guarantees, causing service outages, degraded performance, or data loss from overwhelmed storage. This agent targets Processes (where compute or memory exhaustion halts operations), Data Stores (where storage saturation or lock contention blocks access), and Data Flows (where bandwidth saturation or connection pool exhaustion prevents communication).
Detection Scope
Targeted DFD Element Types
- Process: API endpoints, background workers, data processing pipelines, authentication services, webhook receivers
- Data Store: Databases, caches, message queues, file storage, search indexes
- Data Flow: Network connections, API calls, message bus channels, file upload streams, WebSocket connections
Patterns and Indicators
Resource Exhaustion
- Endpoints accepting unbounded input sizes (request body, file uploads, query parameters)
- Missing request size limits on API gateways or reverse proxies
- Memory-intensive operations triggered by unauthenticated requests
- CPU-intensive computations (regex, compression, encryption) on user-controlled input
- Thread pool exhaustion from long-running synchronous operations
Algorithmic Complexity Attacks
- Regular expressions vulnerable to ReDoS (catastrophic backtracking)
- Hash collision attacks on hash table implementations
- XML parsing vulnerable to billion laughs (entity expansion) or quadratic blowup
- JSON parsing without depth or size limits
- Recursive algorithms on user-controlled data without depth bounds
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.
- 8d ago First seen · 137 lines · 48 tokens per session scan A ea7a9458409e
tachi-denial-of-service is an agent published in the GitHub repository davidmatousek/tachi (92 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,662 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
malware-analyst
Delegates to this agent when the user asks about malware analysis, reverse engineering, binary analysis, disassembly, debugging, sandbox analysis, static analysis, dynamic analysis, or suspicious file triage.
traffic-analyzer
Delegates to this agent when the user wants offline analysis of captured network traffic — dissecting pcaps, extracting credentials and artifacts, reconstructing sessions, identifying protocols and anomalies, and turning a capture into findings. Analyzes captures the user provides; active interception belongs to…
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.
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.