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 mstr-sharma/strategy-automate --skill reference_mosaic_buildgit clone --depth 1 https://github.com/mstr-sharma/strategy-automateWrote 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/reference_mosaic_build)<a href="https://agentmods.dev/skills/mstr-sharma/strategy-automate/reference_mosaic_build"><img src="https://agentmods.dev/badge/skills/mstr-sharma/strategy-automate/reference_mosaic_build/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/reference_mosaic_build"><img src="https://agentmods.dev/badge/skills/mstr-sharma/strategy-automate/reference_mosaic_build.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 | $0.00025 | $0.01518 |
| Opus 5 | $0.00013 | $0.00759 |
| Sonnet 5 | $0.00005 | $0.00304 |
| Haiku 4.5 | $0.00003 | $0.00152 |
Grade A, and why
build-mosaic-model skill location and subcommands 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 6d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: $REPO/skills/build-mosaic-model/SKILL.md
Helper script: $REPO/skills/build-mosaic-model/scripts/build_mosaic.py
Invoke directly; auto-reads tenant defaults and requires MSTR_PASSWORD (or --password) for authenticated calls. Do not hardcode credentials in memory or skill files.
Discovery subcommands (read-only):
auth-probe— confirm login + identity-token flow.list-datasources [--name SUBSTR]— list DB instances, filter by name.list-namespaces --instance NAME|--instance-id ID— schemas in a DB instance.list-tables --instance-id ID --namespace SCHEMA [--match SUBSTR]— tables; uses base64({"ns":…}) for namespaceId under the hood.describe-table --instance-id ID --namespace SCHEMA --table T— columns + types; uses base64({"tbn":…,"ns":…}) for tableId.discover— probes every endpoint variant; useful when porting to a new MSTR version.openapi-summary [--out /tmp/strategy-openapi.yaml]— fetches{base}/api/openapi.yaml, prints title/version/path counts, and selected modeling/data-source paths. Does not require login.openapi-search PATTERN [--context N]— searches localopenapi.yamlfirst, then live OpenAPI; use before coding new endpoint workflows.api-call --method GET --path /api/projects— generic authenticated Strategy REST caller. Use--no-authfor public paths such as/api/openapi.yaml; use--identity-tokenonly for Mosaic data-model Modeling writes;DELETErequires--yes.resolve-users --user NAME_OR_EMAIL/--file users.csv— resolve user IDs before ACL/security/user writes.search-objects --name NAME [--type N] [--subtype N]— Quick Search wrapper for object IDs.get-model-object --kind attribute|fact_metric|legacy_attribute|... --model-id M --object-id O --show-expression-as tokens— read Mosaic-contained or classic schema object definitions.
Build subcommand:
build --name N --source "INSTANCE:SCHEMA:T1,T2,..."(repeatable, for multi-source) — the main one. Flags:--data-serve-mode {connect_live|in_memory|hybrid},--dictionary,--erd,--conformance-map,--fk-map,--attr-cols,--metric-cols,--skip-relationships,--security-filter 'NAME=ATTR_ID[:FORM_ID]=VALUE|USER,USER',--grant 'trusteeId:rights[:user|user_group]',--deny 'trusteeId:rights[:user|user_group]',--translate 'objectId[:SubType]:locale[:field]=text',--certify,--publish.--conformance-map FILE: JSON/YAML{logical_name: [TABLE.COLUMN, ...]}; forces listed columns to collapse into one conformed attribute.--fk-map FILE: JSON/YAML{child_table.child_col: parent_table.parent_col}; normalizes differently-named FKs so they conform.
build-from-config --config spec.yaml— declarative JSON/YAML build; acceptsdictionary,data_dictionary,erd, anderdspaths (seereference_mosaic_config_schema.md).
Quality gate (run after every build, and before publish/certify):
validate-model --model-id M [--fact-tables TBL,TBL] [--strict-orphans] [--diff-against OTHER_ID] [--json]— enforces the rules infeedback_mosaic_build_quality.mdvia the checks catalogued inreference_mosaic_build_validation.md. Emits FAIL/WARN summary + optional JSON report, exits non-zero on failures.--diff-againstflags count regressions (attributes/metrics/relationships dropping vs a prior model id).
User/admin ops:
create-users --file users.csv— dry-run user creation from CSV/JSON/YAML; use--check-existingto resolve duplicates during dry-run.create-users --file users.csv --yes— creates viaPOST /api/users; optional email column creates/api/users/{id}/addresses. Default password can come fromMSTR_NEW_USER_PASSWORD.patch-model-object --kind legacy_attribute|attribute|fact_metric|... --json-file patch.json --before-out before.json --yes— changeset-backed object update with before/after verification.
Individual lifecycle ops (operate on existing models):
set-serve-mode --model-id M --mode {connect_live|in_memory|hybrid}publish --model-id M [--skip-classify] [--poll-seconds N]— for in-memory Mosaic models.--skip-classifybypasses theGET /api/objects/{id}?type=3surface check when you already know the target is a Mosaic model (e.g. chained right afterbuild); saves one project-scoped call against the session cap. Seefeedback_build_mosaic_session_leak.md.wire-relationships --model-id M --hints <file.json|yaml> [--dry-run]— post-build relationship writer with step-3 (self-reference) + step-5 (relationship_table prerequisite) validation. Skips PUTs that would trip8004ccdbor8004ccc7; issues only the ones that will succeed, in one changeset. Seefeedback_mosaic_relationship_wiring.mdfor the hint-file schema.refresh --model-id M --refresh-type {update|add|replace|incremental}delete-model --model-id M --yesset-acl --model-id M --object-id O --sub-type fact_metric --grant 'trusteeId:rights' --deny 'trusteeId:rights'add-security-filter --model-id M --spec 'NAME=ATTR_ID[:FORM_ID]=VALUE|USER,USER'translate --model-id M --entry 'objectId[:subType]:locale[:name|description]=text'certify --object-id O
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.
- 6d ago First seen · 57 lines · 25 tokens per session scan A f9143ef04472
build-mosaic-model skill location and subcommands is a skill published in the GitHub repository mstr-sharma/strategy-automate (2 stars, last pushed 5d ago), licensed MIT. It adds 25 tokens to every session and 1,518 once invoked, about $0.0001 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 2026-09-04.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
supabase
Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…
nornicdb-cypher-queries
Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.
dsql
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key…