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 Encod3d-Sec/TORCH --skill disclosuregit clone --depth 1 https://github.com/Encod3d-Sec/TORCHWrote 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/encod3d-sec/torch/disclosure)<a href="https://agentmods.dev/skills/encod3d-sec/torch/disclosure"><img src="https://agentmods.dev/badge/skills/encod3d-sec/torch/disclosure/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/encod3d-sec/torch/disclosure"><img src="https://agentmods.dev/badge/skills/encod3d-sec/torch/disclosure.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 | $0.00076 | $0.00663 |
| Opus 5.5 | $0.00030 | $0.00265 |
| Sonnet 5.5 | $0.00015 | $0.00133 |
| Haiku 4.5 | $0.00008 | $0.00066 |
Grade A, and why
disclosure 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 1mo 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Disclosure: Finding -> CVE
Turn a proven, novel vulnerability into a coordinated disclosure and a published CVE. Pairs with the research skill (a finding in findings.md) or an engagement FIND. Read [[responsible-disclosure]] first.
Gate (READ FIRST)
- The finding must be proven + reproducible (minimal PoC, affected versions, impact) and novelty-checked (not an existing CVE). If not, go back to the
researchskill. - Confirm you are authorised / in safe-harbor for the target. No authorization -> do not proceed (CFAA / Computer Misuse Act). Research on public software you can lawfully analyze is fine; testing live third-party systems needs permission.
Procedure
- Package the report from the finding: title, affected + fixed/tested versions, CWE class, CVSS vector + score, clear repro steps, minimal PoC, impact, suggested remediation, your contact. Redact any real data.
- Find the contact (in order):
/.well-known/security.txt,SECURITY.md,security@<vendor>, vendor PSIRT, a bug-bounty platform if they run one, GitHub private vulnerability reporting for OSS, else CERT/CC. - Report privately over that channel; PGP-encrypt if a key is published. Professional, specific, non-extortive. Offer to validate the fix.
- Coordinate a timeline - propose ~90 days; track it; escalate to CERT/CC if the vendor goes dark past the deadline.
- Request the CVE: vendor CNA assigns it; for OSS open a GitHub Security Advisory (GitHub issues the CVE); otherwise MITRE CVE request form (CNA of last resort). Supply product, versions, CWE, impact, reference.
- Publish the advisory after fix/deadline: CVE ID, affected/fixed versions, CWE, CVSS, description, PoC, impact, remediation, timeline, credit. Mirror to the researcher's blog/GitHub for the portfolio.
Output
- A ready-to-send disclosure report (draft) and a public advisory (draft) saved under the project:
raw/research/<project>/advisory.md(and the contact + timeline tracked infindings.md). - Update the finding status: candidate -> reported ->
CVE-<id>-> published.
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.
- 1mo ago First seen · 30 lines · 76 tokens per session scan A 928011b37b73
disclosure is a skill published in the GitHub repository Encod3d-Sec/TORCH (336 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 663 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
fto-triage
Freedom-to-operate triage — a structured first look at potentially blocking patents, not an FTO opinion. Use when a product, process, or feature is being evaluated for blocking patents, when asked whether anything stops a launch, or to build a claim-chart first pass against the most plausible patents before patent…
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
terms-of-service
Draft terms of service and a companion privacy notice matched to the product's form and feature modules, not legal advice, delivered as a Word document.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
ai-risk-management
Apply the NIST AI Risk Management Framework (AI RMF 1.0) and adjacent guidance to AI / ML systems — model lifecycle governance, fairness and bias evaluation, robustness, transparency, accountability, third-party model risk, monitoring for drift, and AI incident response. Broader than prompt-injection (which is the…