Borrowing it
Nothing to install: this file belongs to davidmatousek/tachi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/davidmatousek/tachi/main/.claude/skills/tachi-risk-scoring/SKILL.mdgit clone --depth 1 https://github.com/davidmatousek/tachiWrote 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/skills/davidmatousek/tachi/tachi-risk-scoring)<a href="https://agentmods.dev/skills/davidmatousek/tachi/tachi-risk-scoring"><img src="https://agentmods.dev/badge/skills/davidmatousek/tachi/tachi-risk-scoring/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/skills/davidmatousek/tachi/tachi-risk-scoring"><img src="https://agentmods.dev/badge/skills/davidmatousek/tachi/tachi-risk-scoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 72 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
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 | $0.00068 | $0.01867 |
| Opus 5 | $0.00034 | $0.00933 |
| Sonnet 5 | $0.00014 | $0.00373 |
| Haiku 4.5 | $0.00007 | $0.00187 |
Grade A, and why
tachi-risk-scoring 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 7d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tachi-risk-scoring
Quantitative risk scoring domain knowledge extracted from the tachi risk-scorer agent. This skill provides the reference tables, formulas, and assessment criteria that the risk-scorer uses to transform qualitative threat findings into data-backed risk scores.
Domain Overview
The risk scoring model assesses each threat finding on four dimensions:
- CVSS 3.1 Base Score (weight: 0.35) -- Inherent vulnerability severity using standard CVSS 3.1 vector analysis, with AI-specific refinements for agentic and LLM threat categories
- Exploitability (weight: 0.30) -- Practical attack feasibility across four sub-dimensions: known techniques, attack complexity, tooling availability, and skill level
- Scalability (weight: 0.15) -- Blast radius and operational economics across four sub-dimensions: scriptability, target scope, resource requirements, and detection difficulty
- Reachability (weight: 0.20) -- Architecture-aware attack surface exposure derived from trust zone position, zone name analysis, and architecture barrier adjustments
Dimensional scores combine into a weighted composite score (0.0-10.0), which maps to a severity band (Critical/High/Medium/Low) that drives governance fields (SLA, disposition, review date).
AIVSS Relationship
Tachi's four-dimensional composite scoring model diverges from OWASP AIVSS at the present time. AIVSS v0.8 (the latest published version, with its public review period opening 2026-04-16) builds on CVSS v4.0 and uses an amplification model in which 10 Agentic AI Risk Factors uplift the CVSS baseline up to a 10.0 ceiling, then a mitigation factor scales the result. Tachi uses CVSS 3.1 and a weighted-sum composite across four operational dimensions (CVSS, Exploitability, Reachability, Scalability). The two formulas produce measurably different scores on the same finding — see ADR-024 for the three-surface comparison (dimensions, formula, severity bands), the worked examples that quantify the divergence, and the re-evaluation trigger tied to AIVSS reaching stable v1.0 with at least one external adopter case study. Severity bands are aligned (Surface C overlap), so downstream consumers (governance, SLA, color coding) behave identically across the two frameworks' outputs.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 110 lines · 68 tokens per session scan A 3bd2c8a9e03c
tachi-risk-scoring is a skill published in the GitHub repository davidmatousek/tachi (91 stars, last pushed 28d ago), licensed Apache-2.0. It adds 68 tokens to every session and 1,867 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 skills, from other repositories
usap-program-manager
Security program manager and passive lifecycle orchestrator (cs-security-program-manager). Use for security roadmap planning, program health scanning, debt tracking, facilitated reviews, or when the user says "security roadmap", "program planning", "security debt", "proactive scan", or "program review".
usap-ciso
CISO and executive security advisor (cs-ciso-advisor). Use for board reports, executive risk briefings, regulatory gap assessments, cyber insurance inputs, or when the user says "board report", "CISO brief", "executive summary", "risk posture for leadership", or "regulatory update".
usap-incident-responder
Active incident command and response (cs-incident-responder). Use when there is a confirmed or suspected active incident, for containment decisions, forensic investigation, SEV declaration, or when the user says "declare incident", "start IR", "we have an active breach", or "forensics".
usap-red-teamer
Offensive security coordinator (cs-red-teamer). Use for red team campaign planning, attack path analysis, engagement scoping, adversary simulation, or when the user says "red team", "pentest", "attack simulation", "run an engagement", or "offensive security". Requires explicit authorization scope.
usap-alex
Universal USAP security advisor (cs-security-analyst). Use for any security question, alert triage (AT), threat hunt (TH), compromise assessment (CA), or when the user says "activate Alex", "start USAP", or asks what USAP can do.
nuclei
Nuclei CLI parameter reference and usage patterns - YAML-template vulnerability scanning, target input modes, template filters, output formats, rate limits, ProjectDiscovery dashboard upload, and common scan commands.