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-threat-model-lifecyclegit 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-threat-model-lifecycle)<a href="https://agentmods.dev/skills/soliestre/estregenesis/ultrasafe-threat-model-lifecycle"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/ultrasafe-threat-model-lifecycle/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-threat-model-lifecycle"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/ultrasafe-threat-model-lifecycle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 257 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00199 | $0.05857 |
| Opus 5 | $0.00100 | $0.02929 |
| Sonnet 5 | $0.00040 | $0.01171 |
| Haiku 4.5 | $0.00020 | $0.00586 |
Grade A, and why
ultrasafe-threat-model-lifecycle 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.
"reproduction_steps": "1. From an internal-network host (simulated lateral movement), curl billing-service directly with X-Original-User: <victim>. 2. Observe operations executed as victim. 3. Check siem-alert dashboard: How it starts
The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Threat Model / Lifecycle — Ultrasafe Attacker Skill
Role: Pre-release simulated penetration testing from the threat modeling (STRIDE/PASTA) + incident lifecycle + disclosure timing perspective. Tone: lifecycle-systematic — every claim binds to a named threat element + lifecycle phase + (where applicable) a disclosure-timing milestone. Output: Findings emitted via
ULTRASAFE_FINDINGA2A intent (Constellation §13.16) — advisory mode in v0.2.x (report-only; no publish blocking). Position in fan-out: 1 of 8 attacker agents. Sibling roles: ai-llm / web-api / supply-chain / crypto / social-eng / methodology-compliance / synthesizer-cross-axis. SeeUltrasafe.md §15for full topology.
§1 When to invoke
Run this skill when any of the following triggers fire:
- Fan-out dispatch: The orchestrator role (the main agent's Workflow fan-out + the
ultrasafe_run_fanoutMCP tool — Ultrasafe.md §14.1 role mapping) emitsULTRASAFE_RUN_FANOUTwithrole ∈ {threat-model-lifecycle, all}. This is the primary entry path during a release-gate cycle. - PreToolUse hook trigger:
ultrasafe-trigger.cjsmatches a publish-equivalent command (npm publish,pip upload,twine upload,git push --tags <public-remote>,gh release create, container registry push to public registry,gcloud functions deploy --allow-unauthenticated). The 8-agent fan-out runs; this skill is one branch. - Iteration boundary: An
ULTRASAFE_ITERATION_BOUNDARYwas just emitted withclean_signal=falseAND prior iteration's threat-model-lifecycle findings includedseverity ∈ {critical, high}. Re-run for regression check on this axis. - Inbound disclosure:
SECURITY_DISCLOSURE_INTAKEarrives with a vulnerability disclosure timeline question (e.g. "is our 90-day public-disclosure clock correctly anchored?"), ORMPCVD_COORDINATIONarrives needing multi-party timing review. - Manual analyst invocation: User explicitly requests
/ultrasafe threat-modelor analogous (rare — primary path is automated fan-out).
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 · 295 lines · 199 tokens per session scan A d1d098988d3d
ultrasafe-threat-model-lifecycle is a skill published in the GitHub repository SoliEstre/EstreGenesis (8 stars, last pushed 6d ago), licensed Apache-2.0. It adds 199 tokens to every session and 5,857 once invoked, about $0.0010 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?".