ultrasafe-synthesizer

ultrasafe-synthesizer is a skill for Claude Code from SoliEstre/EstreGenesis. It costs 210 tokens per session (7,824 once invoked), scanned A, original, Apache-2.0.

A pre-release security-testing coordinator that combines findings from seven simulated attacker checks. It requires independent agreement before treating a finding as confirmed and produces structured security reports.

In plain words
What is it for?
Use it after the attacker checks finish to remove duplicates, rank risks, record confidence, and evaluate whether the release meets its security conditions.
Why use it?
It helps separate repeated, well-supported security problems from uncertain findings before software is released.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ultrasafe plugin — 8 skills shipped together

Good fit Use it after the attacker checks finish to remove duplicates, rank risks, record confidence, and evaluate whether the release meets its security conditions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/soliestre/estregenesis/ultrasafe-synthesizer
Install

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.

Any agent
npx skills add SoliEstre/EstreGenesis --skill ultrasafe-synthesizer
Clone the repo
git clone --depth 1 https://github.com/SoliEstre/EstreGenesis

Made for: Claude Code.

Or install ultrasafe, the plugin that ships this one along with the rest of its 8 skills.

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 ultrasafe-synthesizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/soliestre/estregenesis/ultrasafe-synthesizer/github.svg)](https://agentmods.dev/skills/soliestre/estregenesis/ultrasafe-synthesizer)
Your own site
<a href="https://agentmods.dev/skills/soliestre/estregenesis/ultrasafe-synthesizer"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/ultrasafe-synthesizer/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.

agentmods 80×15 button for ultrasafe-synthesizer

Your own site · 80×15
<a href="https://agentmods.dev/skills/soliestre/estregenesis/ultrasafe-synthesizer"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/ultrasafe-synthesizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 210 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,824 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00210 $0.07824
Opus 5 $0.00105 $0.03912
Sonnet 5 $0.00042 $0.01565
Haiku 4.5 $0.00021 $0.00782

Measured 12d ago against content hash 3940887108de, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ultrasafe-synthesizer 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.

plugins/ultrasafe/skills/ultrasafe-synthesizer/SKILL.md · 461 lines

How it starts

The opening of the file, as written. The whole thing — 461 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Synthesizer (cross-axis) — Ultrasafe Attacker Skill v0.2.0

Role: Pre-release simulated penetration testing의 retire-barrier 합성 단독. 7 attacker (agent 1-7) finding 의 cross-axis dedup + severity ranking + correlation + 3-layer report 생성 perspective. Tone: synthesis-meta. 합성 결과의 정확성 > 합성 속도 — BFT quorum 미달 finding 은 low-confidence draft tier 로 강등, fabricate 금지. Position in fan-out: Agent 8 (sink). Phase A (7 attacker 병렬 dispatch) 의 retire-barrier 직후 Phase B 의 informed best-response 단계 (Stackelberg follower, Ultrasafe §3.2) 로 진입. Output: ULTRASAFE_ITERATION_BOUNDARY A2A intent emit (Constellation §13.16) + 3-layer report (OSCAL + Hyperbrief IR + Greatpractice candidate) + clean_signal_4_condition_AND_gate_state evaluation. v0.2.x advisory modevalue.advisory: true flag mandatory.


§1 When to invoke

§1.1 Primary triggers

본 skill 은 orchestrator 역할 (메인 에이전트의 Workflow fan-out + MCP ultrasafe_run_fanout — Ultrasafe.md §14.1 역할 매핑) 이 자동 dispatch — 사용자/다른 agent 가 직접 호출하지 않는 게 원칙이에요. 단 다음 시점에 발화:

  1. Retire-barrier auto-fire: 7 attacker (agent 1-7) 모두 ULTRASAFE_FINDING emit 완료 + orchestrator 가 finding bag 을 finalize 한 직후. Tier 1-3 모든 release tier 에서 활성.
  2. Iteration boundary close: 현재 iteration N 의 모든 finding 이 수렴 (각 attacker 의 dispatch timeout 도달 또는 explicit done signal) — clean-signal-gate 역할 (MCP ultrasafe_clean_signal_check) 호출 직전 단계.
  3. Re-synthesis on patch: iteration N 에서 fix 적용 후 iteration N+1 진입 시점 — 직전 boundary snapshot 과 비교한 resolved / regression / persistent / new 4-set diff 계산 강제.
  4. Forced re-synthesis (Hyperbrief MUST-trigger): meta-safety-broker (Ultrasafe §2.5.2) 가 4 mandatory check 중 하나 hit → broker 가 synthesizer 강제 재실행 요청 (단, broker 자체 hit 결과는 synthesizer 가 외부 fact 로 reference, 합성 결과에 inline 하지 않음 — self-spec-gaming 회피).
  5. Catalog version change: OWASP LLM Top 10 / MITRE ATT&CK Enterprise / ISO 27001 Annex A 등 reference catalog 의 version bump 감지 시 (catalog_versions diff). 기존 boundary 의 coverage_percentage_under_catalog 재계산 필요.

Read the full file on GitHub · 461 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. 12d ago First seen · 461 lines · 210 tokens per session scan A 3940887108de

Subscribe to this mod's changes

ultrasafe-synthesizer is a skill published in the GitHub repository SoliEstre/EstreGenesis (8 stars, last pushed 6d ago), licensed Apache-2.0. It adds 210 tokens to every session and 7,824 once invoked, about $0.0011 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.

Related

Other skills, from other repositories

update-agent-context

This skill should be used to keep CLAUDE.md, AGENTS.md, and the skill files themselves compact, current, and internally consistent. It runs in three phases: Phase 1 performs a one-time structural refactor of CLAUDE.md using a Karpathy-inspired behavioral scaffold and derives AGENTS.md from it by stripping Claude…

mostlyharmless-ai/watercooler · 203 tokens

watercooler-onboarding

Bootstrap Watercooler memory for a repository by inspecting local code, docs, CI, git history, and existing Watercooler threads, then writing a small set of durable, provenance-backed seed threads that future agents can query and extend. Use when entering a repo for the first time, seeding a repo with Watercooler…

mostlyharmless-ai/watercooler · 79 tokens

search-threads

Search threads with filters. Supports filters like role:planner, type:Decision, after:2024-01, thread:topic-name, status:OPEN.

mostlyharmless-ai/watercooler · 35 tokens

ppgp

Portable Persistent Goal Protocol for long-running coding-agent work. Use when starting, resuming, handing off, distilling, or closing a substantial software goal across long sessions, context compaction, agent replacement, or other Agent Skills-compatible coding-agent environments.

Fatboy-coder/ppgp · 53 tokens

watercooler-health

Check watercooler system health — MCP server, baseline graph (T1), git auth, GitHub rate limit, and daemons. Use when syncs break or anything in the watercooler stack behaves unexpectedly.

mostlyharmless-ai/watercooler · 49 tokens

recall

Recall project context or answer questions about history and decisions. Use before starting work, when investigating unfamiliar code, or asking "What was decided about X?" / "Why did we choose Y?".

mostlyharmless-ai/watercooler · 41 tokens