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 prismatic7/MASA --skill public-safe-exportgit clone --depth 1 https://github.com/prismatic7/MASAWrote 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/prismatic7/masa/public-safe-export)<a href="https://agentmods.dev/skills/prismatic7/masa/public-safe-export"><img src="https://agentmods.dev/badge/skills/prismatic7/masa/public-safe-export/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/prismatic7/masa/public-safe-export"><img src="https://agentmods.dev/badge/skills/prismatic7/masa/public-safe-export.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00019 | $0.00204 |
| Opus 5.5 | $0.00008 | $0.00082 |
| Sonnet 5.5 | $0.00004 | $0.00041 |
| Haiku 4.5 | $0.00002 | $0.00020 |
Grade A, and why
public-safe-export 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.
What it actually says
Public-safe export
Publication is a new derivative projection, not deletion from a private clone.
- Validate the private source.
- Require an active publication policy and an explicitly permitted evaluation for the exact target.
- Construct from a public allowlist: independently public actors, representations, claims, relations, policies, and contexts only.
- Omit binary assets unless a separately approved sanitized derivative exists.
- Remove private identifiers, local paths, credentials, precise protected locations, private digests, provider settings, and unapproved extension namespaces.
- Record omission and redaction categories without retaining protected values.
- Mint the declared public identity, then validate and audit the finished projection again.
- Refuse when authority is unknown, expired, revoked, or under review.
A secret scan is only defense in depth. It cannot override consent, license, community authority, or policy.
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 · 21 lines · 19 tokens per session scan A e73a29294316
public-safe-export is a skill published in the GitHub repository prismatic7/MASA (0 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 204 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
bo-risk-assessment
A method for assessing operational risks in a process, project, or supplier arrangement using observed facts, possible consequences, and practical response suggestions. It keeps the likelihood of a consequence conditional unless the evidence supports more.
metasounds
Create and modify MetaSound Source assets — add/connect nodes, wire pins, set input defaults, and play procedurally (MetaSoundService). Use when the user asks to create a MetaSound, build or edit a MetaSound graph, add operator/input/output nodes, or generate procedural audio.
unbroker
Find and remove authorized personal information exposures from data brokers and people-search sites with a consent-gated local workflow.
tax-optimizer
Tax optimization strategies including tax-loss harvesting, wash sale rule navigation, asset location optimization, Roth conversion analysis, and charitable giving strategies.
legal-contract-negotiation-review
Analyze counterparty contract changes against agreement/schedules, flag conflicts, and produce severity-rated counterpositions.
legal-demand-letter-response-draft
Map allegations to contract language and draft a response letter with no unintended admissions.