AGENTS.mdA
AGENTS.md from iman/agent-driven-risk-desk-and-skills is an AGENTS.md file: the standing instructions coding agents read in that repo.
mdr add iman/agent-driven-risk-desk-and-skills/AGENTS.md@git:20261104.baeed54Pins git:20261104.baeed54 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 14 of 14 checks passed
- Kind
- AGENTS.md file
- Repository
- iman/agent-driven-risk-desk-and-skills
- Path
AGENTS.md- Versions recorded
- 3
- Latest version
- git:20261104.baeed54, committed Nov 4, 2026
- First version recorded
- Sep 13, 2026
- Size
- 1,432 bytes
- Repository stars
- 3
- License
- a license file GitHub does not identify
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Risk Desk repository guidance The approved initial scope is historical VaR/Expected Shortfall, linear portfolio exposure and stress, and the ORE exposure/XVA adapter. v0.2 (approved by the maintainer on 2026-11-04) adds tail models and VaR/ES backtests, and European option Greeks and revaluation through the Option Desk engine. It also adds covariance and VaR/ES attribution, limits and what-if, liquidity, and historical replay and reverse stress. Its counterparty, credit and capital additions are SA-CCR and exposure profiles, portfolio credit VaR, and FRTB capital pieces. The runtime is under `src/riskdesk`. CLI and MCP use the same functions. Skills live in `plugins/risk-desk/skills`. Before you extend the models, read README.md, THIRD-PARTY.md and docs/IMPLEMENTATION.md. Preserve loss signs, base currency, horizon, source provenance and degraded status. Do not equate historical loss forecasts with risk-neutral valuation. Preserve ORE report levels and unavailable values. Run `python -m pytest -q --color=no`. When you change the ORE adapter, run the pinned ORE example. After a packaging or notice change, rebuild the …
Read the whole file at its exact version.
How to install
mdr add iman/agent-driven-risk-desk-and-skills/AGENTS.md@sha256:26fa5e02c1df76ebThe line at the top of this page pins the label git:20261104.baeed54, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_4sp7hwzhtg7iqyct)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Sep 13, 2026 and Nov 4, 2026, about one every 26 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261104.baeed54 latest | 2026-11-04 | baeed54 | 1,432 B | A | view · diff |
| git:20261104.0499e61 | 2026-11-04 | 0499e61 | 1,345 B | A | view · diff |
| git:20260913.da9f368 | 2026-09-13 | da9f368 | 1,006 B | A | view |
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (1432 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
iman/agent-driven-risk-desk-and-skills · 3 stars · license a license file GitHub does not identify · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_4sp7hwzhtg7iqyct GET https://markdownregistry.com/api/v1/resolve?ref=iman/agent-driven-risk-desk-and-skills/AGENTS.md GET https://markdownregistry.com/api/v1/blob/26fa5e02c1df76eb2f1514809457bf091d8e4b14a965d9d217b2b86d57d54ee9
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.
More from iman/agent-driven-risk-desk-and-skills
Every file in iman/agent-driven-risk-desk-and-skills