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 synthesisengineering/synthesis-skills --skill synthesis-disclosure-policygit clone --depth 1 https://github.com/synthesisengineering/synthesis-skillsWrote 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/synthesisengineering/synthesis-skills/synthesis-disclosure-policy)<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-disclosure-policy"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-disclosure-policy/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/synthesisengineering/synthesis-skills/synthesis-disclosure-policy"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-disclosure-policy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 152 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.
- medium Rogue Agent · line 200 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00107 | $0.02520 |
| Opus 5 | $0.00053 | $0.01260 |
| Sonnet 5 | $0.00021 | $0.00504 |
| Haiku 4.5 | $0.00011 | $0.00252 |
Grade A, and why
synthesis-disclosure-policy 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 11d 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthesis Disclosure Policy
A name blacklist models the wrong thing. Professionals who publish under their own name deliberately say who they work for, who they have worked for, and who they work with — on their sites, in their bios, in their articles. That is conscious, career-positive disclosure. The same professionals also carry genuinely confidential material: client work, internal decisions, private conversations, things an AI collaborator reads in private context every day. A guardrail that treats the NAME as the secret blocks the first category (over-blocking the person's own published biography) while under-protecting the second (a leak rarely needs the blacklisted spelling).
This skill governs disclosure on the axis that matters: approval and provenance. What the person deliberately published is precedent and may be restated. What they did not approve stays closed — no matter how the reference is spelled.
The three disclosure classes
Class P — published precedent. A fact the person personally published on a public surface they author: their sites, bios, articles, social profiles. Restating a Class-P fact in the same register — biography: relationship, role, era, public work — on their public surfaces is allowed. Precedent covers the FACT, not the entity: an employer named in a bio does not make any other statement about that employer public.
Class A — approval required. Any new naming or newly identifying disclosure without precedent: a first-time name, a new kind of fact about a ledgered entity, praise of a named colleague never published before, a case study touching real parties. Default deny. Each approval then BECOMES precedent: it is appended to the ledger with evidence, so the same question is never asked twice.
Class X — protected. Not published even with casual approval; a request to publish gets an explicit challenge naming the risk before proceeding. Contents: negative or critical statements about named or identifiable parties; operational and business specifics — deals, numbers, finances, personnel matters, incidents, unreleased plans, security details, internal decisions — even about Class-P entities; material under NDA or equivalent obligation; other people's private information; and anything sourced from private context with no independent public counterpart.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 234 lines · 107 tokens per session scan A 30df0a543cdc
synthesis-disclosure-policy is a skill published in the GitHub repository synthesisengineering/synthesis-skills (18 stars, last pushed today), licensed Apache-2.0. It adds 107 tokens to every session and 2,520 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
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.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
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.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
nda-review
Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…