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 innae1121-bit/gsghwp --skill automate-hancom-documentsgit clone --depth 1 https://github.com/innae1121-bit/gsghwpWrote 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/innae1121-bit/gsghwp/automate-hancom-documents)<a href="https://agentmods.dev/skills/innae1121-bit/gsghwp/automate-hancom-documents"><img src="https://agentmods.dev/badge/skills/innae1121-bit/gsghwp/automate-hancom-documents/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/innae1121-bit/gsghwp/automate-hancom-documents"><img src="https://agentmods.dev/badge/skills/innae1121-bit/gsghwp/automate-hancom-documents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Anti-Refusal · line 157 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- high Memory Poisoning · line 169 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
- medium Output Handling · line 93 Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
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 | $0.00098 | $0.07039 |
| Opus 5 | $0.00049 | $0.03520 |
| Sonnet 5 | $0.00020 | $0.01408 |
| Haiku 4.5 | $0.00010 | $0.00704 |
Grade A, and why
automate-hancom-documents 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.
How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hancom Document Automation
Start with the production action path: match the request to one public tool and call it. Read a reference only when the work in front of you needs what that reference holds.
Images in a request
Read a visible value directly and call its matching write. For image or PPT structure reconstruction, read references/native-layout.md (identical MCP resource: gsg-hwp-beta://reference/native-layout). That reference is the sole reconstruction workflow; this entrypoint only routes to it.
Non-negotiable rules
- Route every Hancom/HWP edit, analysis, and verification request through the
gsg-hwp-beta-liveMCP and this skill. - Treat a change as successful only after the selected public tool reaches a terminal success result and its operation-specific readback confirms the requested state. A dispatched call or mutation attempt without that readback is not success.
- Choose the most specific public action tool for the user's request. Never invent an API name, cell address, control ID, or hidden execution field.
- Before every public write, choose a caller-owned
operation_id(for example, a UUID) and keep it unchanged until that logical operation reaches a terminal result. Reuse the same ID only when retrying the same payload or recovering a lost response; use a new ID for an intentional second execution, even when its payload is identical. Never derive the ID from the payload. The same ID with different inputs is a conflict. Completed results remain replayable for up to 30 days by default; when the terminal journal exceeds 10,000 records or 64 MiB, the oldest terminal results are evicted first. Never recycle an ID after journal expiry or anot_foundresponse. - Live mode attaches only to the exact active, saved, editable HWP already registered in ROT. It does not open, save, clear, quit, or change history by default. Use
hwp_undoorhwp_redoonly for an explicit history request, andhwp_save_reopen_verifyonly for an explicit save-and-reopen verification request. - Never use
computer-use, Windows UI automation, keyboard/mouse control, or a Python COM document call as a fallback for an HWP operation. If thegsg-hwp-beta-liveMCP is unavailable, disconnected, or returns a closed transport, report that exact state and stop. If a certified native operation is unavailable, return the structured result from the selected HWP tool and stop. - Do not hard-code a document title, page number, table size, or cell map in reusable code.
- When the user asks to analyze or verify how an open HWP page looks, call
hwp_render_page; it preserves document state and uses HWPCreatePageImage. Do not render in the middle of a fill, repeat, sync, or Excel append. For cell text, IDs, merges, or sizes usehwp_inspect_page_fastwithinclude_cells=true.hwp_inspect_structureis not the cell-text readback. hwp_render_pagepublishes each completed PNG at a unique path only afterCreatePageImagefinishes. Active session directories are protected by a worker ownership lock. Released results have a 24-hour TTL and at least a 15-minute client-read grace; cleanup runs at worker startup and every 15 minutes, removes abandoned partial files, and evicts the oldest eligible results when the preview store exceeds 64 MiB.- Document-local styles are read with
hwp_list_styles; never use web search to infer a style ID or local title convention. - For an explicit convention-matching write, read
observed_usage.convention_profileonce and reuse only values the target document actually reports. Check each axis'ssample_count,consistency,complete, variants, scope, andwrite_fields; never turn a conflicting or partial sample into a universal template. - An
unobservedconvention axis is missing evidence, not a reason to refuse the edit. Leave that write field unchanged unless the user supplied it explicitly, and continue with the observed axes the write tool supports. - Table-series tools copy the first table, regenerate each copied automatic-number control, and update only the literal title suffix while preserving the source caption style. Do not follow a successful series call with manual
hwp_add_captioncalls. If caption verification fails, report that failure instead of retrying captions or Undo in a loop. - After a plugin update, stay in the current Codex task and call
hwp_runtime_info. The stable MCP proxy reloads the worker automatically when its source hash changes and emits a tool-list change notification; callhwp_reloadonly to force a reload. Comparemcp,worker_process_id,source_path, andtool_schema_hashbefore continuing.native_bridgeis only the version this build expects;loaded_native_bridgeis the bridge DLL the running Hangul editor actually has mapped, read from its module list, and it is only ever asked ofHwp.exe— Hancom'sHwpApi.exeautomation host never loads the bridge and is not evidence about it. The bridge verdict is reported, never enforced: it does not gate any operation and never by itself makes you stop, refuse, or restart Hangul. Continue the requested work and passnative_bridge_noticethrough to the user whennative_bridge_stateis anything other thanmatched. Onlynative_bridge_state="mismatched"(hangul_restart_required=true) proves a stale DLL is executing right now;not_loadedmeans that Hangul started before this bridge was registered and the next Hangul start picks it up on its own. Never restart Hangul on your own initiative — the user may have unsaved work open; state the notice and let the user decide. If the refreshed direct tool is not yet visible, call it throughhwp_executewith the exact tool name and arguments. - The host may expose this skill directly from the plugin manifest, from a host cache, or through a legacy global Junction. Read the exact displayed
SKILL.mdpath directly without assuming its storage form; do not locate, search, or compare other cache or installation paths. - For table data keyed by visible header labels, use
records. Usecellsonly with verified cell addresses androwsonly when the user supplied an explicitstart_cell. A returnedtarget_idchanges only the target, never the chosen data format. - Explicit 1 mm table rows and columns are supported. To make the physical cell reach that size, set every affected cell to
font_size_pt=1,line_spacing_percent=50, and zero padding; larger inherited text or padding can make HWP expand the cell. HWP stores 1 mm as 283 HWPUNIT, so inspection reports about 0.998 mm per row or column. - For an irregular or partially merged table, use the inspected
CellTopology: actual cell address,row_span,column_span, and physical right/down neighbours. Never synthesizeF1,A11, or an address-distance move sequence. Column and row formatting starts at the requested real cell; merging proceeds only through the recorded neighbour path after the covered owners form a gap-free rectangle. hwp_split_table_cellhas two deliberately different modes. Usesplit_mode="equal"only to subdivide one unmerged physical cell. Usesplit_mode="existing_grid"only to restore the exactrow_span×column_spangrid hidden by a merged cell. Do not split a merged header merely to reach a column for formatting; format the real intersecting cell instead. A requested existing-grid split that does not match the inspected spans must be rejected before mutation.hwp_apply_page_plankeeps each block's absolutebox.top_mm. It does that by writing the planned gap into the paragraph spacing of the block below it, which is the only vertical control a flow layout has; that channel is filled by the compiler and is deliberately absent from the published layout schema, so a layout tool cannot send it and a plan cannot ask for placement by hand. Blocks are emitted top-first regardless of declaration order. A block whose plan box overlaps the one above it, or whose content is taller than its box, is pushed down rather than moved up, and everything after it is measured from where it really ends. Positions land within about 0.2 mm; a plan whose content genuinely exceeds the body is rejected with the millimetres it is short.- Use
hwp_insert_layoutfor live insertion away from the document end.layout.target=currentinserts at the user's collapsed cursor.layout.target=after_pagewithpage=Ninserts at the start of the existing next page and adds one trailing page break, so it creates exactly one isolated page without a blank page; after the last page it appends with one leading page break. Do not add anotherpage_breakblock. Continue to usehwp_append_layoutonly for the document end. - For screenshot or reference-layout reconstruction, restore the evidence-first sequence: call
hwp_analyze_reference_imageonce withfull_scan=true, inspect its overlay/contact sheets, let the model choose semantic elements and loose raster boxes, then callhwp_prepare_image_cropsonce. Mark rectangular photos astight_rasterand annotated maps/drawings/logos asannotated_group; crop preparation resolves the final boundaries and returns a boundary overlay while the model still owns meaning. In native tables, apply visible-surface ownership recursively: group title bands, repeated-item subheading pills, and their body boxes are separate cells or rows, never line-broken text inside one cell. - Never delete and rebuild a page for a local correction. Use
hwp_patch_textfor a sentence or line break, table formatting tools for an existing ordinary table, image replace/size paths for one picture, andreference_layout_patchfor existing reference-grid rows, columns, styles, or edges. Rebuild only when structural inspection proves that no local target can represent the requested correction. headersfilters target tables; it is not a copy of therecordskeys. Use only labels known to be visibly present in the target table. If a page already narrows the request sufficiently, passpagewithout speculativeheaders.
What ships with it
60 files 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.
- agents/openai.yaml 481 B
- references/batch-workflows.md 1.2 KB
- references/data-schema.md 2.3 KB
- references/hybrid-strategy.md 2.6 KB
- references/live-editing.md 369 B
- references/live-inspection.md 8.4 KB
- references/native-editing.md 5.0 KB
- references/native-layout.md 6.8 KB
- references/official-api.md 2.5 KB
- references/qa-operation-internals.md 3.1 KB
- references/ribbon-custom-actions.md 8.6 KB
- references/skill-registration.md 2.5 KB
- references/table-image-office.md 2.2 KB
- references/verification-recovery.md 5.0 KB
- resources/gsg_hwp_pageplan_g02_v1.md 8.2 KB
- resources/gsg_hwp_pageplan_g02_v1.schema.json 34 KB
- resources/gsg_hwp_pageplan_g03_v1.md 6.4 KB
- resources/gsg_hwp_pageplan_g03_v1.schema.json 76 KB
- resources/hancom_official_api_catalog_v1.json 515 KB
- resources/hancom_operation_index_v1.json.gz 151 KB
- scripts/_hwp_hgn1_semantic_parity_codec.py 12 KB runs code
- scripts/_hwp_hgn1_semantic_parity_models.py 2.4 KB runs code
- scripts/_hwp_legacy_tool_oracle_v2.json 1833 KB
- scripts/_hwp_native_graph_errors.py 287 B runs code
- scripts/_hwp_native_graph_primitive.py 25 KB runs code
- scripts/_hwp_native_graph_property_registry.py 7.4 KB runs code
- scripts/_hwp_native_graph_spool.py 5.1 KB runs code
- scripts/_hwp_native_graph_stream.py 29 KB runs code
- scripts/_hwp_native_graph_wire.py 49 KB runs code
- scripts/_hwp_tool_schema_canonical.py 3.1 KB runs code
- scripts/hwp_assembly.py 6.9 KB runs code
- scripts/hwp_automation.py 5.0 KB runs code
- scripts/hwp_checkpoint_signature.py 4.2 KB runs code
- scripts/hwp_codex_skill_install.py 7.1 KB runs code
- scripts/hwp_color_normalization.py 2.8 KB runs code
- scripts/hwp_current_format_insert_contract.py 6.1 KB runs code
- scripts/hwp_custom_action_binding.py 24 KB runs code
- scripts/hwp_custom_action_bridge.py 16 KB runs code
- scripts/hwp_custom_action_runtime.py 31 KB runs code
- scripts/hwp_custom_action_store.py 24 KB runs code
- scripts/hwp_custom_action_tab.py 60 KB runs code
- scripts/hwp_custom_action_tools.py 22 KB runs code
- scripts/hwp_document_convention_axis.py 3.3 KB runs code
- scripts/hwp_document_convention_cache.py 8.2 KB runs code
- scripts/hwp_document_convention_contract.py 2.6 KB runs code
- scripts/hwp_document_convention_profile.py 9.8 KB runs code
- scripts/hwp_document_convention_structure.py 9.7 KB runs code
- scripts/hwp_document_convention_text.py 2.8 KB runs code
- scripts/hwp_document_rebuild.py 13 KB runs code
- scripts/hwp_document_sections.py 7.2 KB runs code
- scripts/hwp_document_style_observation.py 7.8 KB runs code
- scripts/hwp_document_style_profile.py 27 KB runs code
- scripts/hwp_document_style_usage.py 32 KB runs code
- scripts/hwp_document_table_profile.py 10 KB runs code
- scripts/hwp_errors.py 4.2 KB runs code
- scripts/hwp_hgn1_semantic_parity.py 19 KB runs code
- scripts/hwp_hwpx_signature.py 5.2 KB runs code
- scripts/hwp_image_fit.py 3.5 KB runs code
- scripts/hwp_layout_preflight.py 35 KB runs code
- scripts/hwp_live_addon.py 3.5 KB runs code
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.
- 11d ago First seen · 170 lines · 98 tokens per session scan A 240c63ee012b
automate-hancom-documents is a skill published in the GitHub repository innae1121-bit/gsghwp (101 stars, last pushed 10d ago), licensed MIT. It adds 98 tokens to every session and 7,039 once invoked, about $0.0005 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
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.