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-web-api-attackergit 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-web-api-attacker)<a href="https://agentmods.dev/skills/soliestre/estregenesis/ultrasafe-web-api-attacker"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/ultrasafe-web-api-attacker/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-web-api-attacker"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/ultrasafe-web-api-attacker.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 | $0.00169 | $0.07178 |
| Opus 5 | $0.00084 | $0.03589 |
| Sonnet 5 | $0.00034 | $0.01436 |
| Haiku 4.5 | $0.00017 | $0.00718 |
Grade A, and why
ultrasafe-web-api-attacker scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `Bash` — `git log` / `cat package.json` / `npm ls` / `pip list` 등 read-only 명령 한정. **외부 endpoint 호출 금지** (curl / wget / 임의 HTTP). How it starts
The opening of the file, as written. The whole thing — 418 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web/API Attacker — Ultrasafe Attacker Skill (v0.2.0)
Role: Agent 2 of the 8-agent Ultrasafe fan-out — Web/API/infra (WAI) attacker perspective. Tone: web-sec-focused (OWASP × MITRE ATT&CK dual taxonomy 표현, CVSS v4 + EPSS + KEV trump 의 priority 수사). Output:
ULTRASAFE_FINDINGintent emit per finding +attack_path_graph_candidate(v0.2.0 flat list, v0.3+ node/edge promotion). Mode: advisory —value.advisory: true항상 마킹. publish 차단 안 함 (v0.3+ blocking mode 의 wire shape 만 mirror).
본 skill 은 Ultrasafe.md §2.1.2 + §15.2 의 WAI agent role 을 model-invoked skill 로 구현해요. 8-agent fan-out (§15) 의 한 attacker — 본 시각으로 simulated penetration test 수행, finding 을 ULTRASAFE_FINDING A2A intent 로 emit.
§1 When to invoke
본 skill 은 다음 5 trigger 중 하나에서 자동 dispatch 돼요:
- Ultrasafe fan-out 의 axis-set 매칭 —
ultrasafe_run_fanoutMCP tool (Ultrasafe.md §16.1) 호출 시 axis-set 에usf-web-sast-dast또는usf-web-infra포함. 8-agent parallel dispatch (Superscalar Workflow fan-out) 의 한 lane. - PreToolUse hook trigger —
ultrasafe-trigger.cjs(§17 +plugins/ultrasafe/hooks/) 가 publish-equivalent command 감지:npm publish/pip upload/cargo publish/git push --tagsto public remote /gh release create/docker push/helm push. advisory mode 에서는 report-only emit (차단 안 함). - Inbound A2A
SECURITY_DISCLOSURE_INTAKE— 외부 disclosure 수용 시 (Constellation §13.16.5 신규 intent), web-sec category 분류된 disclosure 는 본 attacker 에게 routing → 재현 + cross-axis confirmation. - Iteration boundary re-dispatch —
ULTRASAFE_ITERATION_BOUNDARYemit 후 다음 iteration 진입 시, prior_findings_set 의regression / persistent항목이 web-sec category 라면 재시도. - 명시적 user invoke —
/ultrasafe-web-api-attackerslash 또는 "OWASP Top 10 시각 으로 점검해 줘" 형태의 user 발화 시.
Skip 조건:
- axis-set 이 web-sec 미포함 (AI/LLM only / Crypto only / Social-eng only 등 단일 lane 시).
- 동일
(target_commit_sha, iteration_N)에서 본 agent 가 이미 emit 완료 (idempotency — Constellation §13.13.2 at-least-once 정합). - Read-only fan-out lane 미해당 — 본 skill 자체는 read-only 이지만 publish-equivalent 가 아닌 trigger 라면 skip.
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 · 418 lines · 169 tokens per session scan A b94660bbfd75
ultrasafe-web-api-attacker is a skill published in the GitHub repository SoliEstre/EstreGenesis (8 stars, last pushed 6d ago), licensed Apache-2.0. It adds 169 tokens to every session and 7,178 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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…
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…
search-threads
Search threads with filters. Supports filters like role:planner, type:Decision, after:2024-01, thread:topic-name, status:OPEN.
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.
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.
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?".