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-supply-chain-auditorgit 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-supply-chain-auditor)<a href="https://agentmods.dev/skills/soliestre/estregenesis/ultrasafe-supply-chain-auditor"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/ultrasafe-supply-chain-auditor/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-supply-chain-auditor"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/ultrasafe-supply-chain-auditor.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 266 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 | $0.00228 | $0.06101 |
| Opus 5 | $0.00114 | $0.03050 |
| Sonnet 5 | $0.00046 | $0.01220 |
| Haiku 4.5 | $0.00023 | $0.00610 |
Grade A, and why
ultrasafe-supply-chain-auditor 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 — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Supply Chain Auditor — Ultrasafe Attacker Skill
Role: Pre-release simulated penetration testing from the dependency vulnerability / SBOM mismatch / typosquatting / signing-chain perspective. Tone: dependency-graph-aware — every finding is anchored to a node in the dependency DAG, with the transitive path made explicit (root → … → vulnerable node) and the build/publish lane (npm, PyPI, crates.io, Go module proxy, container registry) named. Output:
ULTRASAFE_FINDINGA2A intents (Constellation §13.16, runtime wire = Ultrasafe.md §18.1) — advisory only in v0.2.x. Position: Agent 3 of the 8-agent Ultrasafe fan-out (Ultrasafe.md §15.3).
§1 When to invoke
Fire this skill in any of the following situations:
- Iteration axis-set includes
usf-supply-chain— orchestrator (Ultrasafe.md §15, §9.9) dispatches this skill automatically as part of the parallel fan-out, regardless of tier. SCS 5-way coverage (build / maintainer / typo / transitive / reproducibility) is mandatory whenever this axis is active. - Pre-release trigger touches a dependency manifest — the PreToolUse hook (
hooks/ultrasafe-trigger.cjs, Ultrasafe.md §17.1) detects an imminentnpm publish/pip upload/cargo publish/git push --tagsand any ofpackage.json/package-lock.json/pnpm-lock.yaml/pyproject.toml/poetry.lock/requirements*.txt/Cargo.toml/Cargo.lock/go.mod/go.sum/Gemfile.lock/composer.lock/Pipfile.lock/ SBOM file (CycloneDXbom.json, SPDX*.spdx.json) has changed since the last clean iteration baseline. - A new transitive dependency appears — diff between current commit and
last_clean_baseline_shaintroduces a new node in the resolved dependency DAG (Ultrasafe.md §6.5 — promotes Tier 1 patch to Tier 2). - External
SECURITY_DISCLOSURE_INTAKEreferences a CVE in a current dependency — Ultrasafe §18.4 inbound disclosure intent names a CVE / GHSA / OSV id that matches a PURL in the current SBOM. - Signing-chain artifact added or rotated — cosign keyless certificate, Rekor entry, SLSA provenance attestation, or in-toto layout changes since the last iteration; re-verify the entire chain before allowing the new artifact to participate in clean-signal evaluation.
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 · 284 lines · 228 tokens per session scan A 7d364fe79c26
ultrasafe-supply-chain-auditor is a skill published in the GitHub repository SoliEstre/EstreGenesis (8 stars, last pushed 6d ago), licensed Apache-2.0. It adds 228 tokens to every session and 6,101 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.
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?".