ultraresearch SKILL.md skillA
ultraresearch from toongri/oh-my-toong-playground is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add toongri/oh-my-toong-playground/ultraresearch@git:20261020.2c60ba9Pins git:20261020.2c60ba9 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- toongri/oh-my-toong-playground
- Path
skills/ultraresearch/SKILL.md- Versions recorded
- 9
- Latest version
- git:20261020.2c60ba9, committed Oct 20, 2026
- First version recorded
- Aug 11, 2026
- Size
- 43,088 bytes
- Repository stars
- 25
- License
- MIT
Maximum-saturation research orchestration as ONE engine with two postures. Fans synchronous explore+librarian+browsing worker waves across codebase, web, official docs, and OSS repos; runs an EXPAND-until-convergence loop driven by leads workers return at each barrier; verifies contested claims through a separate verification pass (executed code for code-shaped claims, oracle citation re-read for the rest); on the explicit research posture, produces a cited REPORT.md…
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
<Role> # ULTRARESEARCH — Maximum-Saturation Research Engine (One Engine, Two Postures) You are the research orchestrator. You run ONE saturation-research engine. The same engine wears two postures depending on who invoked it — but the engine (decompose, saturate, expand until leads dry up, verify in a separate pass, synthesize) is identical across both. Exhaustive coverage is the assignment, not a risk to manage. Under-exploration is the failure here. This is an **umbrella skill**: pre-work grounding is a POSTURE of this engine, not a separate skill. One engine serves explicit research and pre-work grounding alike — they share the same five phases, the same wave loop, the same claim-graph gate. </Role> <Attribution> ## Lineage and attribution - **Engine**: ported from oh-my-openagent's `ultraresearch` saturation-research skill. The async swarm of that source is translated here into synchronous batched Agent waves (see the substrate note in the Engine section). …
Read the whole file at its exact version.
How to install
mdr add toongri/oh-my-toong-playground/ultraresearch@sha256:623c30a78e7512f8The line at the top of this page pins the label git:20261020.2c60ba9, 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_ptwwh5gws53kotv6)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 9 versions of this file, between Aug 11, 2026 and Oct 20, 2026, about one every 9 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261020.2c60ba9 latest | 2026-10-20 | 2c60ba9 | 43,088 B | A | view · diff |
| git:20261020.e3a4aa6 | 2026-10-20 | e3a4aa6 | 43,222 B | A | view · diff |
| git:20261020.067e24c | 2026-10-20 | 067e24c | 43,056 B | A | view · diff |
| git:20261019.85a004e | 2026-10-19 | 85a004e | 42,311 B | A | view · diff |
| git:20260908.2ec781d | 2026-09-08 | 2ec781d | 41,804 B | A | view · diff |
| git:20260811.d4bdf2b | 2026-08-11 | d4bdf2b | 41,806 B | A | view · diff |
| git:20260811.3af5be5 | 2026-08-11 | 3af5be5 | 41,552 B | A | view · diff |
| git:20260811.b4efef2 | 2026-08-11 | b4efef2 | 41,445 B | A | view · diff |
| git:20260811.966ddfe | 2026-08-11 | 966ddfe | 41,234 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (43088 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
toongri/oh-my-toong-playground · 25 stars · license MIT · pushed 2026-10-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ptwwh5gws53kotv6 GET https://markdownregistry.com/api/v1/resolve?ref=toongri/oh-my-toong-playground/ultraresearch GET https://markdownregistry.com/api/v1/blob/623c30a78e7512f89cabc8520529b84e22fd4556c371a419ccabd23c61b7ec7a
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: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.