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 synaptiai/synapti-marketplace --skill disclosure-gatinggit clone --depth 1 https://github.com/synaptiai/synapti-marketplaceWrote 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/synaptiai/synapti-marketplace/disclosure-gating)<a href="https://agentmods.dev/skills/synaptiai/synapti-marketplace/disclosure-gating"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/disclosure-gating/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/synaptiai/synapti-marketplace/disclosure-gating"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/disclosure-gating.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 | $0.00127 | $0.01952 |
| Opus 5 | $0.00063 | $0.00976 |
| Sonnet 5 | $0.00025 | $0.00390 |
| Haiku 4.5 | $0.00013 | $0.00195 |
Grade A, and why
disclosure-gating 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 8d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Disclosure Gating
Owns the boundary between what is true internally and what may be said externally.
Iron Law
NO PUBLIC SENTENCE WITHOUT AN APPROVED CL-#### ROW. Unregistered means unpublishable, regardless of how obviously true it is.
The exception you are about to make — the claim so trivially true it cannot need a row — is how register completeness dies, and completeness is the register's only value.
What the register tracks
Every public-facing capability, metric, reliability, privacy, security, compliance, compatibility, roadmap, and support claim. Each CL-#### row carries the exact proposed wording, its supporting evidence IDs, applicable version and scope, required limitations or conditions, the approving owner, disclosure classification, destination document, and status.
Exact wording matters because approval attaches to a sentence, not to a topic. "We encrypt data at rest" and "all customer data is encrypted at rest" are different claims with different truth conditions, and approving the first does not approve the second.
Column schema and ID grammar: references/register-schemas.md. Policy levels, confidentiality classes, and prohibited vocabulary: references/disclosure-policy-levels.md.
The approval boundary
You may apply a disclosure policy. You may never appoint yourself the business, legal, security, privacy, or communications approver.
Where disclosure.publicClaimApproval is required and no human approval is recorded, the row's status is pending — never approved, never blank. A pending row blocks its sentence, and an unresolved pending row blocks the release gate. That is the intended behaviour, not an obstacle to route around.
| Situation | Handling |
|---|---|
| Technically verified, no approver recorded | pending. Draft the sentence; do not release the document |
| Already appears in existing marketing copy | Existing publication is neither approval nor proof. Re-verify and re-approve, or withdraw |
| Approver rejected it | Record in the rejected section with the reason, then check whether another sentence implies it indirectly |
| Obviously true and trivially checkable | Still needs a row |
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.
- 8d ago First seen · 126 lines · 127 tokens per session scan A 4a921330eb19
disclosure-gating is a skill published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 127 tokens to every session and 1,952 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
alcoa-guard
Use when checking a record / dataset / GMP document for ALCOA+ data integrity — attribution, contemporaneity (backdating), completeness, accuracy (recompute / in-spec), consistency — before a human approves. DEGRADED mode lints any CSV/JSON record against a declared .alcoa.json contract; FULL mode snaps onto an…
create-or-update-concepts
Scan and analyze the project codebase to create or update concept files in agents-context/concepts/ (organized by domains/, source/, shared/) and update the README index and Load-When Cheatsheet.
step2-scope-tasks
Break a specification into ordered task groups with explicit context-awareness directives.
step1-write-spec
Gather requirements through structured Q&A, then formalize into a specification document.
create-pr
Creates a GitHub Pull Request on the current branch with a description focused on WHAT changed (not HOW). Uses emojis in the title and description. Use when the user asks to create a PR, open a pull request, or submit changes for review. Triggers on mentions of PR, pull request, merge request, or code review.
plan-product
Define product mission, vision, target users, and technology stack.