Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add SoliEstre/EstreGenesis --skill ultrasafe-methodology-compliancegit clone --depth 1 https://github.com/SoliEstre/EstreGenesisWrote 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/soliestre/estregenesis/ultrasafe-methodology-compliance)<a href="https://agentmods.dev/skills/soliestre/estregenesis/ultrasafe-methodology-compliance"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/ultrasafe-methodology-compliance/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/soliestre/estregenesis/ultrasafe-methodology-compliance"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/ultrasafe-methodology-compliance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00208 | $0.06142 |
| Opus 5 | $0.00104 | $0.03071 |
| Sonnet 5 | $0.00042 | $0.01228 |
| Haiku 4.5 | $0.00021 | $0.00614 |
Grade A, and why
ultrasafe-methodology-compliance 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 12d 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 — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Methodology / Compliance — Ultrasafe Attacker Skill
Role: Pre-release simulated penetration testing — test methodology gap · coverage cliff · compliance catalog adherence 시각의 attacker perspective. Tone: process-formal. 결정론적·문서적·catalog-anchored. Output:
ULTRASAFE_FINDINGA2A intent (Constellation §13.16, payload = Ultrasafe.md §4 finding output contract 의perspective.primary = "methodology-compliance"variant). v0.2.x 동안value.advisory: truemandatory. 본 skill 의 본질: "secure" 라고 단언하는 게 아니라, 어느 catalog 의 어느 cell 까지 측정했고 어디가 untested 인지 를 결정론적으로 명시하는 것. 무측정 영역은 무결성 주장의 대상이 아니에요.
§1 When to invoke
본 skill 은 model-invoked — orchestrator 역할 (메인 에이전트의 Workflow fan-out — Ultrasafe.md §14.1 역할 매핑) 의 dispatch 또는 MCP tool ultrasafe_run_fanout 호출 시 다음 trigger 중 ANY 충족 시 자동 invoke:
- Publish-equivalent gate: PreToolUse hook (
ultrasafe-trigger.cjs, §17.1) 이 npm publish / pip upload / git push --tags 또는 동급 release 명령을 감지하고 advisory fan-out 을 개시할 때. - Axis-set match: dispatch 의
axis_set에usf-iam-config포함 (본 attacker 의 홈 축) — methodology-coverage · compliance-anchor · test-coverage-cliff 는 축이 아니라 그 축 안의 카탈로그 분류라, 축 집합이 아니라untested_classes[usf-iam-config]에 적어요 + tier ≥ 2. - Iteration boundary continuation: prior iteration 의
iteration_boundary.untested_classes[]가 non-empty 이고 본 attacker 의 axis 가 그 untested 영역과 겹칠 때 (regression baseline 의 secondary-surface diff 회수, §15.7 의 secondary_surface 패턴 정합). - Catalog version bump: 6 catalog 중 하나라도
catalog_version이 prior iteration 대비 변경됐을 때 (예: OWASP WSTG v4.2 → v5.0) — coverage 측정 재산정 강제. - Stop hook clean-signal verify: cycle-end Stop hook (
ultrasafe-clean-signal.cjs, §17.2) 이 4-condition AND-gate (regression-free + monotonic + coverage-floor + consecutive-2-iter) 의 coverage-floor condition 측정을 위해 본 skill 에 coverage 재산정 요청 시.
Skip 조건: tier == 1 (Tier 1 patch 는 sensitivity 낮음, methodology gap audit 비활성) — 단, 1번 trigger (publish-equivalent gate) 는 tier 무관 항상 활성.
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.
- 12d ago First seen · 288 lines · 208 tokens per session scan A 9a26636a5d91
ultrasafe-methodology-compliance is a skill published in the GitHub repository SoliEstre/EstreGenesis (8 stars, last pushed 6d ago), licensed Apache-2.0. It adds 208 tokens to every session and 6,142 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
mcore-testing
Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI parity.
i4h-catheter-navigation-e2e
End-to-end smoke for catheter navigation covering setup, digital twin, DRR, and unit tests. Use when asked to run the full catheter workflow smoke or demo the v0.7 pipeline.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
mcp-app-verification
Comprehensive verification checklists for MCP Apps. Tests with basic-host reference, validates handler-before-connect, text fallback, resource URI linking, single-file bundling, host styling, CSP, and legacy pattern detection.
holohub-app-lifecycle
Use for non-failing HoloHub app work with ./holohub: scaffold, build, run, test, visual evidence, lint, and flow benchmarking.