add-agent-recipe SKILL.md skillA
add-agent-recipe from thinkflowlab/system1-agents is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add thinkflowlab/system1-agents/add-agent-recipe@git:20261006.bcc6793Pins git:20261006.bcc6793 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- thinkflowlab/system1-agents
- Path
.agents/skills/add-agent-recipe/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261006.bcc6793, committed Oct 6, 2026
- First version recorded
- Oct 6, 2026
- Size
- 3,191 bytes
- Repository stars
- 164
- License
- Apache-2.0
Add or update runnable use-case recipes for existing System1-Agents agents, with setup, inference-backend configuration, independent result checks, demo evidence and troubleshooting. Use for recipe authoring; use build-s1a-agent when the task needs a new agent implementation.
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
# Add an agent use-case recipe Read the target checkout's local instructions, [CONTRIBUTING.md](../../../CONTRIBUTING.md), [recipe index](../../../recipes/README.md) and [template](../../../recipes/TEMPLATE.md). Recipes live at `recipes/<use-case>/README.md`, with small safe fixtures beside them. Resolve the concrete task, existing agent/front and observable completion check. Trace its state source, enumerated choices, execution tools and evaluator; do not assume a `DONE` signal establishes success. If it needs a new runtime behavior or backend integration, identify that separate scope before presenting a runnable recipe for it. Check the actual CLI, extras, environment precedence and artifact paths. State the decision model's checkpoint/revision and library or serving engine separately from the chat model's role. For System1-Omni, verify both worker support and the agent client's modality/question/window/hardware contract. Pin both repositories and record a missing client or configuration instead of inventing a supported command. Write one complete setup → run → verify path, then clearly identified alternatives. Use a bounded task and …
Read the whole file at its exact version.
How to install
mdr add thinkflowlab/system1-agents/add-agent-recipe@sha256:637e522785a6c36fThe line at the top of this page pins the label git:20261006.bcc6793, 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_gh5kccw2yumzjbns)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, all committed on Oct 6, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261006.bcc6793 latest | 2026-10-06 | bcc6793 | 3,191 B | A | view · diff |
| git:20261006.7c7e3be | 2026-10-06 | 7c7e3be | 2,708 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 (3191 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
thinkflowlab/system1-agents · 164 stars · license Apache-2.0 · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_gh5kccw2yumzjbns GET https://markdownregistry.com/api/v1/resolve?ref=thinkflowlab/system1-agents/add-agent-recipe GET https://markdownregistry.com/api/v1/blob/637e522785a6c36f56911e98b69fde5f1d68b3345ae6d3785313260115d007f4
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.