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 antikas/open-investment-model --skill openim-research-and-architecturegit clone --depth 1 https://github.com/antikas/open-investment-modelWrote 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/antikas/open-investment-model/openim-research-and-architecture)<a href="https://agentmods.dev/skills/antikas/open-investment-model/openim-research-and-architecture"><img src="https://agentmods.dev/badge/skills/antikas/open-investment-model/openim-research-and-architecture/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/antikas/open-investment-model/openim-research-and-architecture"><img src="https://agentmods.dev/badge/skills/antikas/open-investment-model/openim-research-and-architecture.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 | $0.00047 | $0.00590 |
| Opus 5 | $0.00023 | $0.00295 |
| Sonnet 5 | $0.00009 | $0.00118 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
openim-research-and-architecture 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 12d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenIM research and architecture
An open, MIT-licensed, vendor-neutral reference model for institutional investment management, comprising a service-domain decomposition of the buy-side firm and a canonical entity model.
Use the MCP tools supplied by this plugin. They query a released, local model index and return the exact model version and official source with every result.
Required workflow
- Call
openim_get_identityfirst. Treat its version, scope, maturity, licence, and official URLs as authoritative for the answer. - Choose the narrowest retrieval tool for the task. Do not reconstruct model facts from memory.
- Follow a search or requirement mapping with
openim_getfor each element used in a substantive recommendation. - Cite the returned
sourceUrlorofficialSource, and state the returnedmodelVersion. - Separate retrieved model content from your interpretation. State any gap rather than inventing an element or relationship.
Tool selection
- Use
openim_searchto find business domains, service domains, service operations, entities, relationships, glossary terms, or exports. - Use
openim_getwhen an identifier is known or when full documented content and provenance are needed. - Use
openim_map_requirementfor a plain-language business, data, or architecture requirement. Its matches are deterministic keyword-ranked candidates, not an architecture decision. - Use
openim_list_exportsto locate released machine-readable artefacts and their versioned sources. - Use
openim_get_identityto establish canonical identity, release, model counts, licence, and maturity.
For an adjacent-standard question, search for the named standard, retrieve the matching material, and report only the relationship supported by the returned text. An identity-level alignsWith link is evidence of alignment context, not equivalence or endorsement.
Answer contract
Include:
- the direct answer or proposed mapping;
- the OpenIM identifiers and titles supporting it;
- the released model version;
- official source links returned by the tools;
- limitations, unmatched requirements, and interpretation clearly labelled.
What ships with it
1 file 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.
- 12d ago First seen · 47 lines · 47 tokens per session scan A 1d8be5e99bbd
openim-research-and-architecture is a skill published in the GitHub repository antikas/open-investment-model (4 stars, last pushed 11d ago), licensed MIT. It adds 47 tokens to every session and 590 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
stp-automation
Measure and raise straight-through processing (STP) rates in securities operations through zero-touch, exception-based processing. Use when measuring STP rates and analyzing manual touchpoints in an existing process, replacing review-all workflows with exception-based processing, evaluating RPA vs API-based vs hybrid…
fee-billing
Build and manage advisory fee billing operations from fee schedule design through calculation, collection, revenue recognition, and compliance disclosure. Use when the user asks about tiered or breakpoint fee schedules, billing cycle configuration, AUM valuation for billing, direct-debit vs invoice collection, GAAP…
time-value-of-money
Calculate present value, future value, NPV, IRR for projects and loans, loan payments, and amortization schedules across all compounding conventions. Use when the user asks about discounting cash flows, valuing an annuity or perpetuity, comparing investments with different timing, building a mortgage amortization…
return-calculations
Compute and compare investment return metrics including TWR, MWR (dollar-weighted IRR on portfolio cash flows), CAGR, and annualized returns. Use when the user asks about portfolio performance calculation, comparing manager returns, linking sub-period returns, understanding why different return methods give different…
statistics-fundamentals
Apply statistical methods to financial data including descriptive statistics, covariance estimation, regression, hypothesis testing, and resampling. Use when the user asks about return distributions, correlation between assets, building a covariance matrix, running a CAPM regression, testing whether alpha is…
settlement-clearing
Guide the understanding and management of trade settlement and clearing processes. Use when designing settlement workflows for T+1 compliance, understanding DTC/NSCC/FICC clearing infrastructure, analyzing continuous net settlement (CNS) netting obligations, setting up institutional trade processing (affirmation…