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 provos/ironcurtain --skill json-schema-emailsgit clone --depth 1 https://github.com/provos/ironcurtainWrote 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/provos/ironcurtain/json-schema-emails)<a href="https://agentmods.dev/skills/provos/ironcurtain/json-schema-emails"><img src="https://agentmods.dev/badge/skills/provos/ironcurtain/json-schema-emails/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/provos/ironcurtain/json-schema-emails"><img src="https://agentmods.dev/badge/skills/provos/ironcurtain/json-schema-emails.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 | $0.00062 | $0.00446 |
| Opus 5 | $0.00031 | $0.00223 |
| Sonnet 5 | $0.00012 | $0.00089 |
| Haiku 4.5 | $0.00006 | $0.00045 |
Grade A, and why
json-schema-emails 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 10d 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
emails.json schema
The fetch state writes .workflow/emails/emails.json and the summarize
state reads it. The file is a single JSON array of email objects. The
canonical JSON Schema is in the sibling file schema.json; this document
explains the fields and their semantics.
Top-level shape
A JSON array. Each element is an email object. The array order is preservation order — the consumer renders emails in the order they appear, so the producer should write them in the order it wants them rendered (typically newest-first as returned by the API).
Email object fields
All fields are required and must be strings unless noted.
sender— the From address. FormatName <[email protected]>if the source provides a display name, else the bare address.recipient— the To addresses, comma-separated. If the source has multiple To recipients they are joined with,(comma + space). CC and BCC are not represented in this schema.subject— the email subject line, verbatim. Empty string is allowed if the source has no subject; do not substitute "(no subject)".date— the date as it appears in the source headers (RFC 2822 or whatever the API returns). Do not reformat or normalize the timezone.body— the message body as plain text. If the source is HTML, the producer is responsible for stripping tags before writing. Newlines are preserved; tabs are replaced with two spaces.
Validating
The sibling schema.json is a draft-2020-12 JSON Schema. Tooling that
needs to validate the file structurally should load it from there; this
document is the human-readable companion.
What ships with it
1 file 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.
- 10d ago First seen · 42 lines · 62 tokens per session scan A f6a61b970912
json-schema-emails is a skill published in the GitHub repository provos/ironcurtain (602 stars, last pushed 4d ago), licensed Apache-2.0. It adds 62 tokens to every session and 446 once invoked, about $0.0003 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
09-for-sure
Run an iterative agent loop that retries until a runnable success condition passes. Use when the user says "for sure", "keep trying until", or wants guaranteed completion against a success command. Not for one-shot tasks or uncheckable goals.
maintenance
Update mcp-reporter dependencies, adopt SDK changes, reconcile development workflows, and verify the CLI and library.
field-test
Exercise mcp-reporter's collected reports through in-memory, stdio, HTTP and compiled Node entry points.
test-driven-development
TDD workflow — Red, Green, Refactor cycle with practical examples.
ci-cd-pipeline
Design and implement CI/CD pipelines for automated testing and deployment.
resume-ai-validator
A command-line tool for testing ResumeAI, a service that analyzes and improves résumés. It checks both the service's API and the user interface through complete user journeys.