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 icedq-tools/mcp-server --skill icedq-mapping-doc-rulesgit clone --depth 1 https://github.com/icedq-tools/mcp-serverWrote 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/icedq-tools/mcp-server/icedq-mapping-doc-rules)<a href="https://agentmods.dev/skills/icedq-tools/mcp-server/icedq-mapping-doc-rules"><img src="https://agentmods.dev/badge/skills/icedq-tools/mcp-server/icedq-mapping-doc-rules/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/icedq-tools/mcp-server/icedq-mapping-doc-rules"><img src="https://agentmods.dev/badge/skills/icedq-tools/mcp-server/icedq-mapping-doc-rules.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.05462 |
| Opus 5.5 | $0.00000 | $0.02185 |
| Sonnet 5.5 | $0.00000 | $0.01092 |
| Haiku 4.5 | $0.00000 | $0.00546 |
Grade A, and why
icedq-mapping-doc-rules 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.
How it starts
The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GOAL
Extract ALL quality rules from a column mapping spec. ONE Validation rule per table (all checks combined). Rule types: Validation, Duplicate, Checksum, Recon, Pushdown.
Output contract: this skill designs and gets approval; it does NOT call create_* tools. The
approved Rule Plan is converted into rule specs (references/rule-spec.md) and handed to
icedq-author-rules Build mode, which validates, creates, and confirms each rule. Every
decision approved here travels in the spec — Build mode never re-asks (populated field = approved).
STEP 0 — PARSE DOC
Format detection:
- Excel/CSV/Word table: find header row; map labels to signal fields below. Ignore decorative title rows.
- dbt schema.yml: not_null→Mandatory; unique→UniqueKey; accepted_values→ApprovedValues; relationships→FK Pushdown
- JSON Schema: required→Mandatory; enum→ApprovedValues; maxLength→MaxLen; pattern→Format; $ref→FK Pushdown
- Prose: scan for "Validations:", "Business Rules:", "Constraints:", "Data Requirements:" headings
Signal field aliases:
| Signal | Common column names |
|---|---|
| Source col | Source Column, SRC Column, From Column, Source Field |
| Target col | Target Column, TGT Column, DW Column, Destination |
| Mandatory | Mandatory?, Required?, Nullable?, Not Null |
| Unique key | Unique Key?, PK?, Business Key?, Natural Key? |
| Transform | Transformation, Logic, Mapping Rule, ETL Logic |
| Approved values | Approved Values, Domain, Valid Values, Lookup |
| Format | Format, Pattern, Regex, Data Format |
| Min/Max Length | Min Length, Max Length, Length |
| FK | Cross-Table, FK Reference, References, Lookup Table |
| Business rule | Business Rule, Acceptance Criteria, DQ Rule, Notes |
| Severity | Severity, Priority, Criticality, Risk Level |
YES synonyms: Y YES TRUE 1 Required NOT NULL Mandatory. NO synonyms: N NO FALSE 0 Optional NULL Nullable blank.
Missing columns — infer:
- No Mandatory col → check target DDL for NOT NULL; scan Business Rule text for "must not be null"
- No Unique Key → scan Business Rule for "must be unique"/"primary key"/"no duplicate"
- No Approved Values → extract from Business Rule or Transform text
- No Min/Max Length → infer from type: VARCHAR(N)→max=N; CHAR(N)→exact=N
- No Format → extract regex/format strings from Business Rule text
What ships with it
5 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.
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.
- 1mo ago Changed · -77 lines · -169 tokens per session af49bb6e8b23
- 1mo ago First seen · 442 lines · 169 tokens per session scan A 05fee0f3cd38
icedq-mapping-doc-rules is a skill published in the GitHub repository icedq-tools/mcp-server (1 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 5,462 tokens. 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 2026-09-08.
Other skills, from other repositories
spreadsheet-create-verify-gate
Create or edit Excel workbooks with openpyxl-specific pitfall handling, anchored preflight audit, and deterministic post-write proof that every criterion is satisfied.
spreadsheet-direct-verification
Use a deterministic Python/openpyxl inspection pass to verify workbook structure, counts, marked rows, and output-file existence when delegated spreadsheet summaries seem inconsistent.
define-data
Standalone Phase 4 of SAP UI testing. Authors one tests/ /test-cases/TC-XXX.data.md requirement spec per case marked dataRequired: yes — choosing the narrowest correct source (sql/static/generated/seeded), and generating upload fixtures in the EXACT file format the program parses (xlsx vs csv). Validates that every…
spreadsheet-proof-gate-merged-fedf41-merged
The derived skill is complete and provides a meaningful enhancement.
xz-cases
A generator for acceptance-test checklists covering the core feature changes between specified software versions. It writes the checklist to an XLSX spreadsheet, a format used by Microsoft Excel and similar programs.
postman-test-implementation
Converts an approved company-format testcase workbook (from api-test-design + company-testcase-format) into one Postman collection and one Postman environment, using conventions learned from real company artifacts and this project's src/postman builders. Does not execute anything and does not decide what to test.