desk-data-auditor Claude Code subagentA
desk-data-auditor from iman/agent-driven-options-desk-and-skills is a Claude Code subagent: a helper Claude Code hands a task to, with its own instructions.
mdr add iman/agent-driven-options-desk-and-skills/.claude/agents/desk-data-auditor.md@git:20260908.9626273Pins git:20260908.9626273 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 14 of 14 checks passed
- Kind
- Claude Code subagent
- Repository
- iman/agent-driven-options-desk-and-skills
- Path
.claude/agents/desk-data-auditor.md- Versions recorded
- 3
- Latest version
- git:20260908.9626273, committed Sep 8, 2026
- First version recorded
- Aug 31, 2026
- Size
- 4,844 bytes
- Repository stars
- 11
- License
- a license file GitHub does not identify
Check the freshness, completeness and internal consistency of the artifacts on disk before anyone reports from them. Use before publishing or acting on desk output, after a scheduled run, when numbers look surprising, or when the user asks whether the data is any good.
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
You audit the artifacts, not the market. Everything you need is in the artifact directory and every artifact carries its own meta block. ## The checks, in order of what has burned this desk before **Freshness.** Compare `spot_asof` with `generated_utc` and with today. A spot from the last settled close is correct on a weekend and misleading if reported as current. Say which session each number belongs to. **Degradation.** Any artifact with `degraded` true, and its reason. This is the first thing to report, never a footnote. **Refusals and skips.** `skipped.no_iv`, `legs_skipped_without_iv`, `discarded_paths`, `insufficient_paths`, `unmarkable` positions. These are the pipeline working correctly, and a large count still changes what the output can support. For a refusal that cites no price, check whether the contract has a positive mid. A positive mid can come from a quote or a last trade. Missing two-sided quotes alone do not explain this refusal. The note "as a bisection that gave up" reports a provider volatility near a power of two. This is a rejection heuristic, not proof of how the provider computed the value. Report the refusal counts and their effect on coverage. …
Read the whole file at its exact version.
How to install
mdr add iman/agent-driven-options-desk-and-skills/.claude/agents/desk-data-auditor.md@sha256:3d84c266ef184ba1The line at the top of this page pins the label git:20260908.9626273, 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_s6owwiveshpsndzy)
1 badge image fetches in 30 days. What the badge shows.
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it: what changed in iman/agent-driven-options-desk-and-skills/.claude/agents/desk-data-auditor.md since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.
Got a copy of desk-data-auditor.md from somewhere else? Ask it: where did my desk-data-auditor.md come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.
Versions
The registry has recorded 3 versions of this file, between Aug 31, 2026 and Sep 8, 2026, about one every 4 days.
Watch this file (sign in, one email per new version)
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260908.9626273 latest | 2026-09-08 | 9626273 | 4,844 B | A | view · diff |
| git:20260831.ed610db | 2026-08-31 | ed610db | 4,088 B | A | view · diff |
| git:20260831.06e0205 | 2026-08-31 | 06e0205 | 2,089 B | A | view |
Installed this file, say at desk-data-auditor.md? Drop it here to learn which saved version you have and what changed since. Your browser works out its SHA-256 fingerprint and sends only that; the file itself never leaves your computer.
Or paste its contents
Your agent can run this same check on the agent markdown files you have installed, up to 50 in one ask. Add the registry once:
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it to check the files you have installed. No key and no account.
From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies
In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies
No sha256sum on your machine? shasum -a 256 prints the same lines.
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (4844 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-options-desk-and-skills · 11 stars · license a license file GitHub does not identify · pushed 2026-11-10 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_s6owwiveshpsndzy GET https://markdownregistry.com/api/v1/resolve?ref=iman/agent-driven-options-desk-and-skills/.claude/agents/desk-data-auditor.md GET https://markdownregistry.com/api/v1/blob/3d84c266ef184ba13719fdf798b4bcf34df1aa11023aafd724875e65e3d0b084
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: which agent file does what.