tachi-repudiation

tachi-repudiation is an agent for Claude Code from davidmatousek/tachi. It costs 41 tokens per session (1,470 once invoked), scanned A, original, Apache-2.0.

A security analysis agent that looks for actions a user or service could deny because the system lacks reliable audit evidence.

In plain words
What is it for?
It reviews external users and processes for missing audit trails, insufficient log detail, log tampering risks, and altered timestamps.
Why use it?
It helps expose missing or weak records that make investigations, accountability, and compliance difficult.

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 external users and processes for missing audit trails, insufficient log…

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/repudiation

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-repudiation

README.md
[![agentmods](https://agentmods.dev/badge/agents/davidmatousek/tachi/repudiation.svg)](https://agentmods.dev/agents/davidmatousek/tachi/repudiation)
Your own site
<a href="https://agentmods.dev/agents/davidmatousek/tachi/repudiation"><img src="https://agentmods.dev/badge/agents/davidmatousek/tachi/repudiation.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,470 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 $0.00041 $0.01470
Opus 5 $0.00020 $0.00735
Sonnet 5 $0.00008 $0.00294
Haiku 4.5 $0.00004 $0.00147

Measured 3d ago against content hash 7a5a150bafec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tachi-repudiation 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 3d 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/repudiation.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Metadata

category: stride
threat_class: R
dfd_targets: [External Entity, Process]
owasp_references:
  - "OWASP Top 10 2021 A09:2021 — Security Logging and Monitoring Failures"
  - "OWASP API Security 2023 API9 — Improper Inventory Management"
  - "CWE-778: Insufficient Logging"
  - "CWE-223: Omission of Security-Relevant Information"
  - "CWE-117: Improper Output Neutralization for Logs"
  - "MITRE ATT&CK T1070: Indicator Removal"
output_schema: ../../../schemas/finding.yaml

Repudiation Threat Agent

Purpose

Detects threats where a user or system can deny having performed an action, and the system lacks sufficient evidence to prove otherwise. Repudiation failures undermine accountability, forensic investigation, and compliance obligations. This agent targets External Entities (where users can deny actions they performed) and Processes (where services fail to produce tamper-evident audit trails of their operations).

Detection Scope

Targeted DFD Element Types

  • External Entity: End users, API consumers, third-party integrations, administrative users, automated clients
  • Process: Application services, payment processors, authorization services, data export services, administrative interfaces

Patterns and Indicators

Missing Audit Trails

  • Security-sensitive operations (login, logout, permission changes) not logged
  • Financial transactions without immutable audit records
  • Data deletion operations without pre-deletion snapshots or tombstone records
  • Administrative actions (user creation, role assignment) missing from audit logs
  • API calls that modify state without recording the authenticated caller identity

Insufficient Log Detail

  • Logs missing actor identity (who performed the action)
  • Logs missing timestamp with sufficient precision (sub-second for high-frequency systems)
  • Logs missing source context (IP address, session ID, request correlation ID)
  • Logs missing the before-and-after state for data modifications
  • Generic log messages that cannot distinguish between different operation types

Read the full file on GitHub · 120 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. 3d ago First seen · 120 lines · 41 tokens per session scan A 7a5a150bafec

Subscribe to this mod's changes

tachi-repudiation is an agent published in the GitHub repository davidmatousek/tachi (90 stars, last pushed 24d ago), licensed Apache-2.0. It adds 41 tokens to every session and 1,470 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.