Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mstr-sharma/strategy-automatenpx agentmods add skills/mstr-sharma/strategy-automate/strategy-validationWrote 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/mstr-sharma/strategy-automate/strategy-validation)<a href="https://agentmods.dev/skills/mstr-sharma/strategy-automate/strategy-validation"><img src="https://agentmods.dev/badge/skills/mstr-sharma/strategy-automate/strategy-validation/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/mstr-sharma/strategy-automate/strategy-validation"><img src="https://agentmods.dev/badge/skills/mstr-sharma/strategy-automate/strategy-validation.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 | $0.00131 | $0.03160 |
| Opus 5.5 | $0.00052 | $0.01264 |
| Sonnet 5.5 | $0.00026 | $0.00632 |
| Haiku 4.5 | $0.00013 | $0.00316 |
Grade A, and why
strategy-validation 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 18d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Strategy Data Validation
Use this skill whenever a model (especially a freshly built or modified Mosaic model) needs to be proven data-correct before it's marked shippable. Every build should close with validation or an explicit validation-pending note. The reference source can be whatever trusted artifact is closest to ground truth — this skill is not Mosaic-only.
Validation is always comparative. There is no universal "model is correct" check without first selecting what it should match: an existing Mosaic model, a classic/legacy semantic-layer report or model, a raw warehouse query, a flat file, an external system/API, or a saved REST fixture. If no trusted comparator is available yet, say that clearly and mark the build not shippable pending validation.
Scope
Owns the paired-query validator (skills/build-mosaic-model/scripts/strategy_validate_models.py) and the Test Center API areas — Baseline Test, Comparison Test, Test Center Settings, Storage Sync File, and the internal Test Center file store and baseline-result files (python3 skills/strategy-platform/scripts/strategy_api.py ops --tag strategy-validation --internal). Structural checks are build_mosaic.py validate-model; fixing a model is build-mosaic-model.
When to invoke
- Right after a new Mosaic build completes (before reporting "done").
- After a schema change (added/removed tables, attribute re-mapping, metric override, relationship edit).
- Before a production publish or refresh.
- During a legacy → Mosaic migration, to prove the Mosaic model reproduces classic report answers.
- On demand when a user doubts a number they saw in a dashboard.
Reference sources (pluggable)
Pick the reference based on what's available and trusted. Record the selected reference type and reference object/source in the validation report.
- Another Mosaic model — clone-reference pattern. Query through the Mosaic MCP
querytool withproject="<project name from get_projects>"(the model must be certified to be visible), or direct Trino with schema = project name lowercased. Best when validating a clone-and-remap or an alternate live/in-memory variant of the same source. - Classic/legacy semantic-layer report — run the classic report via
/api/reports/{id}/instances+ JSON Data API, or query the classic project attributes/metrics through the Modeling Service. Best during legacy-to-Mosaic migrations; seememory/reference_strategy_legacy_to_mosaic_mining.md. - Flat file (CSV / Parquet / JSON) — a snapshot export, hand-curated gold set, or auditor-supplied file. Load locally with
csv/json/ DuckDB / Pandas. Best when the warehouse is read-once (compliance exports, audit reconciliation). - Direct warehouse SQL — bypass the semantic layer entirely and query Snowflake / BigQuery / Oracle / etc. with raw SQL. Best for "does the semantic-layer math match the raw warehouse?" checks.
- External system / REST output — saved output from a prior run (canary fixture), an externally-hosted reference API, a source application, or a previous inventory snapshot. Best for regression: "does today's build still match yesterday's numbers?"
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.
- 18d ago Changed · +29 lines · +53 tokens per session ca725d909d51
- 1mo ago First seen · 153 lines · 78 tokens per session scan A 27914e5e6298
strategy-validation is a skill published in the GitHub repository mstr-sharma/strategy-automate (2 stars, last pushed yesterday), licensed MIT. It adds 131 tokens to every session and 3,160 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…