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 agentmods add skills/ahmedawan-oracle/claude-code-plugins/workbook-authoringnpx skills add ahmedawan-oracle/claude-code-plugins --skill workbook-authoringgit clone --depth 1 https://github.com/ahmedawan-oracle/claude-code-pluginsWrote 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/ahmedawan-oracle/claude-code-plugins/workbook-authoring)<a href="https://agentmods.dev/skills/ahmedawan-oracle/claude-code-plugins/workbook-authoring"><img src="https://agentmods.dev/badge/skills/ahmedawan-oracle/claude-code-plugins/workbook-authoring.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 | $0.00030 | $0.09868 |
| Opus 5 | $0.00015 | $0.04934 |
| Sonnet 5 | $0.00006 | $0.01974 |
| Haiku 4.5 | $0.00003 | $0.00987 |
Grade A, and why
workbook-authoring 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 5d 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 — 568 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workbook Authoring (Regenerated JSON, Runtime-Valid)
Use this skill to generate full workbook JSON that is both schema-shaped and plugin-runtime-valid for shipped template families.
Scope
- Two-mode authoring:
regenerate_workbookis the primary/default path (full deterministic regeneration).modify_existingis additive and limited to supported scoped edits (filter-value edits, add filter-bar filter, title edits).- Multi-canvas + multi-viz workbooks are allowed and expected when the use case requires them; do not default to single-canvas/single-viz unless explicitly requested.
- Disk-first output is mandatory.
- Public API/token flows are out of scope.
- Server sample workbook inspection is fallback-only.
- Save-target mode is independent from generation mode: update requests should replace existing workbook by default.
Preflight: OAC MCP connection (fail fast)
- Before anything else, confirm the
oac-mcp-servertools are live — this skill reads the OAC catalog through them (discovery,describe_data, save-validation). Probe once with a cheaporacle_analytics-search_catalogcall (or checkclaude mcp list→oac-mcp-server ✔ Connected).- If dead / unauthenticated: STOP with an actionable message — do not
proceed into catalog resolution (it would fail deep with an opaque error,
or worse, read an empty result as "datasets don't exist"). Tell the user:
from the customer project directory, run:
Then restart/reconnect Claude Code (env -u OAC_URL -u OAC_MCP_USER -u OAC_MCP_PASSWORD -u OAC_ADMIN_USER -u OAC_ADMIN_PASSWORD \ aidp-fusion-autopilot dashboard mcp-setup \ --connector-js <path-to-oac-mcp-connect.js>/mcp→ reconnectoac-mcp-server) so the tools activate, then re-invoke. Theenv -u ...wrapper lets the project.envwin over any global shell OAC profile. If this workbook request is part of the Fusion Autopilot journey, write.aidp/autopilot/resume.mdfirst withskills/aidp-fusion-autopilot/write_resume_checkpoint.py. MCP servers bind at session start; the connection cannot be established mid-session. (Autopilot front-loads this as Step 1b.) - A save-unavailable connection is fine (disk-first fallback below); a fully dead connection is not.
- If dead / unauthenticated: STOP with an actionable message — do not
proceed into catalog resolution (it would fail deep with an opaque error,
or worse, read an empty result as "datasets don't exist"). Tell the user:
from the customer project directory, run:
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.
- 26.05/model/calculation-contracts.v1.json 6.3 KB
- 26.05/model/dv-intelligence-contract.v1.json 7.3 KB
- 26.05/model/edit-operation-contracts.v1.json 4.5 KB
- 26.05/model/filter-profiling-contracts.v1.json 3.7 KB
- 26.05/model/map-network-allowlists.v1.json 2.4 KB
- 26.05/model/metadata-to-json-mapping.v1.json 37 KB
- 26.05/model/plugin-type-aliases.v1.json 12 KB
- 26.05/model/presentation-polish-contracts.v1.json 5.9 KB
- 26.05/model/regenerate-workbook-adapter-contract.v1.json 3.6 KB
- 26.05/model/regenerate-workbook-contract.v1.json 23 KB
- 26.05/model/roots/workbook_root_1134.json 2.4 KB
- 26.05/model/runtime-path-registry.v1.json 1.7 KB
- 26.05/model/runtime-profile-contracts.v1.json 28 KB
- 26.05/model/semantic-role-contracts.v1.json 4.1 KB
- 26.05/model/semantic-validation-rules.v1.json 57 KB
- 26.05/model/support-window.v1.json 2.0 KB
- 26.05/model/validation/schema-registry-profile.json 7.3 KB
- 26.05/model/version-field-catalog.json 3.5 KB
- 26.05/model/viz-resolution-profiles.v1.json 37 KB
- 26.05/model/viz-runtime-catalog.v1.json 76 KB
- 26.05/model/workbook-authoring-constraints.json 2.8 KB
- 26.05/model/workbook-model-index.json 1.9 KB
- 26.05/schemas/_common_schemas_1_.js 25 KB runs code
- 26.05/schemas/_common_schemas_10_.js 62 KB runs code
- 26.05/schemas/_common_schemas_11_.js 83 KB runs code
- 26.05/schemas/_common_schemas_12_.js 4.6 KB runs code
- 26.05/schemas/_common_schemas_2_.js 27 KB runs code
- 26.05/schemas/_common_schemas_3_.js 21 KB runs code
- 26.05/schemas/_common_schemas_4_.js 17 KB runs code
- 26.05/schemas/_common_schemas_5_.js 13 KB runs code
- 26.05/schemas/_common_schemas_6_.js 18 KB runs code
- 26.05/schemas/_common_schemas_7_.js 34 KB runs code
- 26.05/schemas/_common_schemas_8_.js 24 KB runs code
- 26.05/schemas/_common_schemas_9_.js 20 KB runs code
- 26.05/schemas/workbook_1.0.0_requestVariableParameterBindings.js 673 B runs code
- 26.05/schemas/workbook_1134_.js 2.3 KB runs code
- 26.05/schemas/workbook-schema-manifest.json 1.0 KB
- 26.05/templates/area_time.json 16 KB
- 26.05/templates/bar_basic.json 16 KB
- 26.05/templates/bar_with_canvas_filter_control.json 24 KB
- 26.05/templates/combo_basic.json 29 KB
- 26.05/templates/donut_basic.json 18 KB
- 26.05/templates/gantt_basic.json 12 KB
- 26.05/templates/line_time.json 16 KB
- 26.05/templates/map_basic.json 18 KB
- 26.05/templates/network_basic.json 19 KB
- 26.05/templates/parallel_coordinates_basic.json 11 KB
- 26.05/templates/performance_tile_basic.json 7.2 KB
- 26.05/templates/pivot_basic.json 9.6 KB
- 26.05/templates/sankey_basic.json 19 KB
- 26.05/templates/scatter_basic.json 23 KB
- 26.05/templates/table_basic.json 7.9 KB
- 26.05/templates/template-index.json 21 KB
- 26.05/templates/waterfall_basic.json 16 KB
- 26.07/model/calculation-contracts.v1.json 6.3 KB
- 26.07/model/dv-intelligence-contract.v1.json 7.3 KB
- 26.07/model/edit-operation-contracts.v1.json 4.5 KB
- 26.07/model/filter-profiling-contracts.v1.json 3.7 KB
- 26.07/model/map-network-allowlists.v1.json 2.4 KB
- 26.07/model/metadata-to-json-mapping.v1.json 37 KB
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.
- 5d ago First seen · 568 lines · 30 tokens per session scan A 84e33b922699
workbook-authoring is a skill published in the GitHub repository ahmedawan-oracle/claude-code-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 9,868 once invoked, about $0.0002 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
dcf-model
Build discounted cash flow valuation workbooks in Excel.
audit-xls
Audit a spreadsheet for formula accuracy, errors, and common mistakes. Scopes to a selected range, a single sheet, or the entire model (including financial-model integrity checks like BS balance, cash tie-out, and logic sanity). Triggers on "audit this sheet", "check my formulas", "find formula errors", "QA this…
google-drive-sheets
Find, read, export, edit, and manage the user's Google Drive, Docs, Sheets, and Slides through per-user OAuth.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
excel-basic-statistics-and-routing
Skill "excel-basic-statistics-and-routing" from OpenSenseNova/SenseNova-Skills, covering skill steps, 保存区间提取与汇总结果 and 保存筛选与统计结果.
large-file-parquet-analysis-and-highlight
当Excel文件总行数超过1万行时,通过转换为Parquet格式提升读取性能,提取目标指标并计算最大值,最后将结果输出为Excel并对特定行进行高亮标注。.