jsonbill

jsonbill is a skill for Claude Code, Codex from quailyquaily/mistermorph. It costs 17 tokens per session (959 once invoked), scanned A, original, Apache-2.0.

A service that turns structured JSON data into PDF invoices or statements through the JSONBill API. An API is a way for software services to exchange requests and results.

In plain words
What is it for?
Use it to create invoice or statement PDFs from JSON, including JSON read from a local file, and retrieve the resulting document link.
Why use it?
It removes the need to build PDF document generation and invoice formatting yourself. It also describes a way to keep API credentials out of prompts and logs.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to create invoice or statement PDFs from JSON, including JSON read from a local file, and retrieve the resulting document link.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/quailyquaily/mistermorph/jsonbill
Install

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.

Any agent
npx skills add quailyquaily/mistermorph --skill jsonbill
Clone the repo
git clone --depth 1 https://github.com/quailyquaily/mistermorph

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for jsonbill

README.md
[![agentmods](https://agentmods.dev/badge/skills/quailyquaily/mistermorph/jsonbill/github.svg)](https://agentmods.dev/skills/quailyquaily/mistermorph/jsonbill)
Your own site
<a href="https://agentmods.dev/skills/quailyquaily/mistermorph/jsonbill"><img src="https://agentmods.dev/badge/skills/quailyquaily/mistermorph/jsonbill/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.

agentmods 80×15 button for jsonbill

Your own site · 80×15
<a href="https://agentmods.dev/skills/quailyquaily/mistermorph/jsonbill"><img src="https://agentmods.dev/badge/skills/quailyquaily/mistermorph/jsonbill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 959 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 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 Data Exfiltration · line 64
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 79
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 96
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00017 $0.00959
Opus 5 $0.00009 $0.00479
Sonnet 5 $0.00003 $0.00192
Haiku 4.5 $0.00002 $0.00096

Measured 11d ago against content hash 31df9381ce50, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

jsonbill 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.

assets/skills/jsonbill/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

JSONBill (portable, safe)

API base: https://api.jsonbill.com

This skill is designed to call the JSONBill REST API without ever exposing API keys/tokens to the LLM:

  • Do not ask the user to paste an API key/token.
  • Do not place secrets in prompts, logs, or tool parameters.
  • Use a host-side credential mechanism (e.g. “credential profile”, “secret manager”, “vault”, env var injection) so the agent never sees the secret value.

Prerequisites (host configuration)

The host must be configured (outside this skill) with:

  • A credential profile id (recommended): jsonbill
  • A secret reference (example): JSONBILL_API_KEY
  • A binding that injects the credential into HTTP requests (commonly: Authorization: Bearer <secret>)

Endpoints

  • Create task: POST /tasks/docs
  • Poll task: GET /tasks/{trace_id}
  • PDF URL: GET /tasks/{trace_id}.pdf (usually you can return this URL without downloading)

Portable pseudocode

Notes:

  • If the user input is a local file path, you MUST read the file and parse its JSON first. Never send local paths to external APIs.
  • Prefer downloading the PDF and sending the file if the platform supports it; otherwise return the PDF URL.
Inputs:
  invoice_source: either (a) JSON object, or (b) local file path to a JSON file

Definitions (abstract operations; map to your agent/tooling):
  READ_TEXT(path) -> string
  PARSE_JSON(text) -> object
  HTTP_JSON(method, url, auth_profile, json_body, headers?) -> {status, json, text}
  HTTP_BYTES(method, url, auth_profile, headers?) -> {status, bytes, content_type}
  SLEEP(seconds)
  SAVE_BYTES(path, bytes) -> saved_path
  SEND_FILE(saved_path, filename, caption?)  (optional; if your platform supports files)

Procedure:
  if invoice_source is a local path:
    invoice_text = READ_TEXT(invoice_source)
    invoice_json = PARSE_JSON(invoice_text)
  else:
    invoice_json = invoice_source

  # 1) Create async generation task
  create = HTTP_JSON(
    method="POST",
    url="https://api.jsonbill.com/tasks/docs",
    auth_profile="jsonbill",
    json_body=invoice_json
  )
  assert create.status is 2xx
  trace_id = create.json.trace_id (or create.json.data.trace_id depending on API)
  assert trace_id is not empty

  # 2) Poll until done (backoff recommended)
  interval = 1.0
  deadline_seconds = 60
  elapsed = 0
  while true:
    poll = HTTP_JSON(
      method="GET",
      url="https://api.jsonbill.com/tasks/" + trace_id,
      auth_profile="jsonbill",
      json_body=null
    )
    assert poll.status is 2xx
    status = poll.json.status
    if status == 3:
      break
    if status == 4:
      raise error with poll.json (or poll.text)
    SLEEP(interval)
    elapsed += interval
    if elapsed >= deadline_seconds:
      raise timeout
    interval = min(interval * 1.5, 8.0)

  # 3) PDF download
  pdf_url = "https://api.jsonbill.com/tasks/" + trace_id + ".pdf"
  if platform supports sending files:
    pdf = HTTP_BYTES(
      method="GET",
      url=pdf_url,
      auth_profile="jsonbill",
      headers={"Accept": "application/pdf"}
    )
    assert pdf.status is 2xx
    assert pdf.bytes is non-empty
    saved = SAVE_BYTES("jsonbill/invoice_" + trace_id + ".pdf", pdf.bytes)
    SEND_FILE(saved, filename="invoice.pdf", caption="Your PDF invoice")
  else:
    return pdf_url

Read the full file on GitHub · 119 lines

Changes

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.

  1. 11d ago First seen · 119 lines · 17 tokens per session scan A 31df9381ce50

Subscribe to this mod's changes

jsonbill is a skill published in the GitHub repository quailyquaily/mistermorph (80 stars, last pushed yesterday), licensed Apache-2.0. It adds 17 tokens to every session and 959 once invoked, about $0.0001 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.