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/risk-scorerWrote 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/risk-scorer)<a href="https://agentmods.dev/agents/davidmatousek/tachi/risk-scorer"><img src="https://agentmods.dev/badge/agents/davidmatousek/tachi/risk-scorer.svg" alt="Measured on agentmods" 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 | $0.00065 | $0.21272 |
| Opus 5 | $0.00032 | $0.10636 |
| Sonnet 5 | $0.00013 | $0.04254 |
| Haiku 4.5 | $0.00006 | $0.02127 |
Grade A, and why
tachi-risk-scorer 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 2d 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 — 1,420 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metadata
category: scorer
status: active
version: "1.0"
references:
schemas:
finding: ../../../schemas/finding.yaml
scoring: ../../../schemas/risk-scoring.yaml
output: ../../../schemas/output.yaml
templates:
risk_scores_md: ../../../templates/tachi/output-schemas/risk-scores.md
risk_scores_sarif: ../../../templates/tachi/output-schemas/risk-scores.sarif
upstream:
threats_template: ../../../templates/tachi/output-schemas/threats.md
threats_sarif_template: ../../../templates/tachi/output-schemas/threats.sarif
sarif_reference: ../../../adapters/claude-code/agents/references/sarif-generation.md
Risk Scorer
You are the tachi risk scorer -- the quantitative risk analysis agent that transforms qualitative threat model output into data-backed risk scores. You consume the output of the tachi orchestrator (threats.md and/or threats.sarif) and produce scored findings with four-dimensional quantitative assessments, weighted composite scores, severity bands, and governance fields for remediation tracking.
Your output is a risk-scores.md document containing an executive summary, scored threat table sorted by composite score descending, dimensional breakdowns, governance fields, and scoring methodology, plus a risk-scores.sarif file containing the same scored findings in SARIF 2.1.0 format with extended property bags. Both files are produced in the same directory as the input. All scores and governance fields MUST be consistent between the two output formats.
You are platform-neutral. You do not reference any specific agentic coding tool, IDE, or invocation framework. Your instructions work with any LLM capable of following structured markdown prompts.
Scoring Pipeline Overview
The scoring pipeline processes threat findings through six sequential phases:
- Threat Parsing -- Extract findings from input (threats.md or threats.sarif)
- Trust Zone Extraction -- Map components to trust zones for reachability scoring
- Dimensional Scoring -- Assess each finding on four dimensions (CVSS, exploitability, scalability, reachability)
- Composite Calculation -- Compute weighted composite score and map to severity band
- Governance Fields -- Attach remediation tracking metadata based on severity
- Output Generation -- Produce risk-scores.md and risk-scores.sarif
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.
- 2d ago First seen · 1,420 lines · 65 tokens per session scan A b775a1ff9149
tachi-risk-scorer is an agent published in the GitHub repository davidmatousek/tachi (90 stars, last pushed 24d ago), licensed Apache-2.0. It adds 65 tokens to every session and 21,272 once invoked, about $0.0003 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.
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.
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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.