workflow-authoring SKILL.md skillA
workflow-authoring from letta-ai/letta-code is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add letta-ai/letta-code/workflow-authoring@git:20261028.a8f8e4bPins git:20261028.a8f8e4b in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- letta-ai/letta-code
- Path
src/skills/builtin/workflow-authoring/SKILL.md- Versions recorded
- 10
- Latest version
- git:20261028.a8f8e4b, committed Oct 28, 2026
- First version recorded
- Sep 21, 2026
- Size
- 15,501 bytes
- Repository stars
- 3,790
- License
- Apache-2.0
Reference for writing a Workflow tool script (script API and gotchas, pipeline-vs-barrier rules, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.
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
# Workflow authoring reference A workflow structures work across many subagents — to be comprehensive (decompose and cover in parallel), to be confident (independent perspectives and adversarial checks before committing), or to take on scale one context can't hold (migrations, audits, broad sweeps). The script is where you encode that structure: what fans out, what verifies, what synthesizes. When you do call the Workflow tool, the right move is often **hybrid**: scout inline first (list the files, scope the diff, find the modules) to discover the work-list, then call Workflow to pipeline over it, passing the list via `args`. You don't need to know the shape before the *task* — only before the *orchestration step*. Common single-phase workflows you can chain across turns: - **Understand** — parallel readers over relevant subsystems → structured map - **Design** — judge panel of N independent approaches → scored synthesis - **Review** — dimensions → find → adversarially verify - **Research** — multi-modal sweep → deep-read → synthesize - **Migrate** — discover sites → transform each → verify For larger work, run several in sequence — read each result before deciding …
Read the whole file at its exact version.
How to install
mdr add letta-ai/letta-code/workflow-authoring@sha256:5bb48defcb824e0cThe line at the top of this page pins the label git:20261028.a8f8e4b, 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_omau4py7pkl6dfyr)
6 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 10 versions of this file, between Sep 21, 2026 and Oct 28, 2026, about one every 4 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261028.a8f8e4b latest | 2026-10-28 | a8f8e4b | 15,501 B | A | view · diff |
| git:20261019.0ace9fa | 2026-10-19 | 0ace9fa | 15,476 B | A | view · diff |
| git:20261012.c0c8ee9 | 2026-10-12 | c0c8ee9 | 15,358 B | A | view · diff |
| git:20261008.1d057dd | 2026-10-08 | 1d057dd | 14,963 B | A | view · diff |
| git:20261008.86f1456 | 2026-10-08 | 86f1456 | 14,939 B | A | view · diff |
| git:20261008.f6dba4a | 2026-10-08 | f6dba4a | 14,039 B | A | view · diff |
| git:20260928.ba084c5 | 2026-09-28 | ba084c5 | 13,981 B | A | view · diff |
| git:20260928.bddbc99 | 2026-09-28 | bddbc99 | 13,738 B | A | view · diff |
| git:20260925.be3434d | 2026-09-25 | be3434d | 12,123 B | A | view · diff |
| git:20260921.b25271a | 2026-09-21 | b25271a | 12,059 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 (15501 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
letta-ai/letta-code · 3,790 stars · license Apache-2.0 · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_omau4py7pkl6dfyr GET https://markdownregistry.com/api/v1/resolve?ref=letta-ai/letta-code/workflow-authoring GET https://markdownregistry.com/api/v1/blob/5bb48defcb824e0c3205a6b4a491dd4ddba084be87484fbd1565c8b0697bb82f
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.
More from letta-ai/letta-code
Every file in letta-ai/letta-code