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 bobadilla-tech/requiems-api-skills --skill data-integrity-post-batchgit clone --depth 1 https://github.com/bobadilla-tech/requiems-api-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/bobadilla-tech/requiems-api-skills/data-integrity-post-batch)<a href="https://agentmods.dev/skills/bobadilla-tech/requiems-api-skills/data-integrity-post-batch"><img src="https://agentmods.dev/badge/skills/bobadilla-tech/requiems-api-skills/data-integrity-post-batch.svg" alt="Measured on agentmods" 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 | $0.00075 | $0.01199 |
| Opus 5 | $0.00037 | $0.00600 |
| Sonnet 5 | $0.00015 | $0.00240 |
| Haiku 4.5 | $0.00007 | $0.00120 |
Grade A, and why
data-integrity-post-batch 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Endpoint
POST https://requiems.xyz/v1/systems/input/validate/batch
Batch Input Validate
Validates and scores a batch of up to 50 contact records in a single request. Each record is processed independently — one item failing does not affect others. Returns per-item email, phone, and text validation results with quality scores, normalized values, plus batch-level aggregates including total, valid_count, invalid_count, and average_quality_score.
Parameters
| Name | Type | Required | Location | Description |
|---|---|---|---|---|
items |
array | yes | body | Array of contact records to validate. Each item must include email and phone. Text is optional. Min: 1, Max: 50. |
Response Example
{
"data": {
"results": [
{
"index": 0,
"email": {
"valid": true,
"normalized": "[email protected]",
"quality_score": 1,
"disposable": false
},
"phone": {
"valid": true,
"normalized": "+1 415-555-0001",
"quality_score": 1
},
"text": null,
"overall_quality_score": 1,
"error": null
},
{
"index": 1,
"email": {
"valid": true,
"normalized": "[email protected]",
"quality_score": 1,
"disposable": false
},
"phone": {
"valid": true,
"normalized": "+1 415-555-0002",
"quality_score": 1
},
"text": null,
"overall_quality_score": 1,
"error": null
}
],
"total": 2,
"valid_count": 2,
"invalid_count": 0,
"average_quality_score": 1
},
"metadata": {
"timestamp": "2026-06-16T21:28:14Z"
}
}
Response Fields
| Field | Type | Description |
|---|---|---|
results |
array | List of validation results, one per input item. Preserves the original submission order via the index field. |
results[].index |
integer | Zero-based position of the item in the original request array. |
results[].email |
object | Email validation result. Null when email was not provided for this item. |
results[].email.valid |
boolean | True when the email passes syntax and MX validation. |
results[].email.normalized |
string | Normalized form of the email address. Null when syntax is invalid. |
results[].email.quality_score |
number | Email quality score from 0.0 to 1.0. Penalized by invalidity, disposable domain, and suggestions. |
results[].email.disposable |
boolean | True when the email domain is a known disposable or temporary provider. |
results[].phone |
object | Phone validation result. Null when phone was not provided for this item. |
results[].phone.valid |
boolean | True when the phone number is valid and dialable. |
results[].phone.normalized |
string | Normalized phone number in international format. Null when the number is invalid. |
results[].phone.quality_score |
number | Phone quality score from 0.0 to 1.0. Penalized by invalidity, VoIP, virtual, landline, and unknown type. |
results[].text |
object | Text analysis result. Null when text was not provided for this item. |
results[].overall_quality_score |
number | Weighted quality score from 0.0 to 1.0 combining email and phone fields only. Weights are email 0.5 and phone 0.4, adjusted proportionally when one field is absent. Text does not currently contribute to this score — scoring will be enabled once toxicity_score is available from the sentiment service. Returns 0.0 when only text is provided. |
results[].error |
string | Error message when this item could not be processed due to an unexpected failure, such as a service timeout or malformed input. Null when the item was processed successfully, regardless of whether the fields passed validation or not. |
total |
integer | Total number of items in the batch. |
valid_count |
integer | Number of items where all provided fields have valid set to true. |
invalid_count |
integer | Number of items where at least one provided field has valid set to false, or where processing failed due to a timeout or unexpected error. |
average_quality_score |
number | Average of overall_quality_score across all successfully processed items. Items that failed due to a timeout or unexpected error are excluded from this average. |
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 · 103 lines · 75 tokens per session scan A 1b011526641f
data-integrity-post-batch is a skill published in the GitHub repository bobadilla-tech/requiems-api-skills (2 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 1,199 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
humanizar
Reescreve textos em português brasileiro para soarem mais humanos e naturais, reduzindo padrões típicos de escrita gerada por IA sem alterar fatos, argumento ou intenção. Use quando o texto em PT-BR parecer genérico, burocrático ou gerado por IA, ou quando o usuário pedir para "humanizar", "dar vida", "tirar cara de…
human-ai
Rewrites English text so it reads as written by a person, without AI writing tics. Removes machine language patterns and AI slop, restores semantic entropy, and injects voice and personality. Use when ENGLISH text reads as generic, bland, or AI-generated - or when asked to "humanize", "de-slop", "remove AI patterns"…
agent-ready-cloudflare
Audit and improve website readiness for AI agents using the Cloudflare "Is It Agent Ready?" scanner (isitagentready.com). Covers scanning via API, interpreting results, generating implementation prompts, and fixing every check. Use when the user mentions "agent ready", "isitagentready", "AI agent scan", "agent…
aidlc-master
Runs the AWS AI-DLC (AI-Driven Development Life Cycle) methodology end to end: an adaptive three-phase workflow (Inception → Construction → Operations) with human approval gates, a full audit trail, and all artifacts in aidlc-docs/. Use when the user says "Using AI-DLC", "AI-DLC", "AIDLC", "aidlc-master", or asks for…
coolify-operator
Master Coolify operator for self-hosted deployment platform. Use when the user mentions 'coolify', 'deploy on coolify', 'list/restart/redeploy applications', 'view coolify logs', 'coolify API/CLI', 'manage coolify servers/databases/apps', or 'coolify context'. Automates deployments and management via REST API or…
okf-open-knowledge-format
Create, validate, and enrich Open Knowledge Format (OKF) bundles — the open spec for representing organizational knowledge as markdown files with YAML frontmatter. Use when the user mentions 'OKF', 'Open Knowledge Format', 'knowledge bundle', 'OKF bundle', 'create a knowledge base for agents', 'validate OKF', 'convert…