form-fill

form-fill is a skill for Claude Code, Codex from airmang/python-hwpx-automation. It costs 38 tokens per session (449 once invoked), scanned A, original, Apache-2.0.

A workflow for filling existing HWPX documents, a document format used by Hancom Office, across fields, table cells, file paths, and text anchors.

In plain words
What is it for?
Use it for government, school, or public-sector forms that combine native fields, labeled tables, standard locations, and body text.
Why use it?
It reduces accidental layout changes and ensures all approved values are checked and applied as one operation.

Skill for Claude CodeCodex

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

Good fit Use it for government, school, or public-sector forms that combine native fields, labeled tables, standard locations, and body text.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/airmang/python-hwpx-automation/form-fill
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 airmang/python-hwpx-automation --skill form-fill
Clone the repo
git clone --depth 1 https://github.com/airmang/python-hwpx-automation

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 form-fill

README.md
[![agentmods](https://agentmods.dev/badge/skills/airmang/python-hwpx-automation/form-fill/github.svg)](https://agentmods.dev/skills/airmang/python-hwpx-automation/form-fill)
Your own site
<a href="https://agentmods.dev/skills/airmang/python-hwpx-automation/form-fill"><img src="https://agentmods.dev/badge/skills/airmang/python-hwpx-automation/form-fill/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 form-fill

Your own site · 80×15
<a href="https://agentmods.dev/skills/airmang/python-hwpx-automation/form-fill"><img src="https://agentmods.dev/badge/skills/airmang/python-hwpx-automation/form-fill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 449 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 pass 7 Sept 2026
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 $0.00038 $0.00449
Opus 5.5 $0.00015 $0.00180
Sonnet 5.5 $0.00008 $0.00090
Haiku 4.5 $0.00004 $0.00045

Measured 1mo ago against content hash 6cd6e5e56841, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

form-fill 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 1mo 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.

examples/skills/form-fill/SKILL.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Form Fill

Use this workflow when a government, school, or public-sector form already exists and approved values must be applied across mixed locator types with minimal drift.

Tool Order

  1. Keep the approved source immutable and choose a distinct output path.
  2. Read visible structure with list_form_fields, get_document_outline, get_paragraphs_text, and get_table_map.
  3. Build one strict hwpx.mixed-form-plan/v1 with the required nativeField, labelCell, canonicalPath, and bodyAnchor operations.
  4. Call analyze_form_fill(plan=...) and resolve every ambiguity before applying.
  5. Call apply_form_fill(plan=compiledPlan) so all operations commit once or roll back together.
  6. Call verify_form_fill(plan=compiledPlan, expected_output_revision=...) and retain the unified receipt.
  7. Keep apply_evalplan_fill as the dedicated evaluation-plan route and compose_exam as the separate exam route.
  8. Use fill_form_field, batch_replace, or set_table_cell_text only for narrow retained compatibility cases.

Minimize Layout Drift

  • Keep table shapes unchanged unless the compiled plan explicitly permits a structural operation.
  • Prefer existing fields and anchors instead of inserting paragraphs.
  • Block on ambiguous or multi-match locators rather than selecting the first result.
  • Require open-safety, byte-preservation, reopen, and privacy evidence before handoff.

When To Inspect Package Parts

  • The same visible label appears in multiple places and analysis cannot choose uniquely.
  • The form contains unsupported drawing objects or opaque package structures.
  • The canonical locator evidence is insufficient to authorize a write.

Honest Limitations

  • The canonical mixed-form route does not replace the dedicated evaluation-plan or exam workflows.
  • Complex seals or unsupported drawings still require their dedicated tools or manual review.
  • The source and output must remain distinct; never treat an in-place compatibility edit as the canonical transaction.

Read the full file on GitHub · 39 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. 1mo ago First seen · 39 lines · 38 tokens per session scan A 6cd6e5e56841

Subscribe to this mod's changes

form-fill is a skill published in the GitHub repository airmang/python-hwpx-automation (68 stars, last pushed 4d ago), licensed Apache-2.0. It adds 38 tokens to every session and 449 once invoked, about $0.0002 per session on Opus 5.5. 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.