workflow-delegated-implementation SKILL.md skillA
workflow-delegated-implementation from lugassawan/swe-workbench is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add lugassawan/swe-workbench/workflow-delegated-implementation@git:20260828.71a6399Pins git:20260828.71a6399 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- lugassawan/swe-workbench
- Path
skills/workflow-delegated-implementation/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260828.71a6399, committed Aug 28, 2026
- First version recorded
- Jul 26, 2026
- Size
- 7,458 bytes
- Repository stars
- 3
- License
- MIT
Phase-2 delegation protocol for workflow-development — conditional scope/complexity gate, dispatch to code-impl with a structured brief (goal, file_set, verify_cmd), summary-only verification result consumption (re-read prevention). Distinct from superpowers:subagent-driven-development, which orchestrates tasks in parallel by default; the delegation protocol gates on scope, groups by commit-axis cohesion, and enforces a diff-free return contract.
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: Delegated Implementation Phase-2 delegation strategy. When scope or complexity warrants it, the orchestrator groups related file changes, dispatches each cohesive group to a focused `swe-workbench:code-impl` sub-agent, and consumes a concise verification summary instead of re-reading changed files. This keeps the orchestrator context lean and enables safe sequential (or opt-in parallel) execution. **Announce at start:** "I'm using workflow-delegated-implementation to delegate [N] change groups to code-impl." ## When to invoke Delegate when **any** of the following is true: | Condition | Threshold | Rationale | |---|---|---| | File count | > 5 distinct files | Reading every diff fills orchestrator context | | Module count | > 2 distinct modules/packages | Cross-module reasoning benefits from focused agents | | Dependency depth | Changes span ≥ 2 dependency layers | Isolated agents reduce reasoning surface | | Complexity | Non-trivial logic in ≥ 2 separate concerns | Each concern deserves focused attention | | Explicit request | Orchestrator decides delegation is cleaner | Orchestrator judgment overrides thresholds | …
Read the whole file at its exact version.
How to install
mdr add lugassawan/swe-workbench/workflow-delegated-implementation@sha256:ffc0d0b30efb7e8cThe line at the top of this page pins the label git:20260828.71a6399, 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_ywyobvk3z54d2y7d)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 26, 2026 and Aug 28, 2026, about one every 8 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260828.71a6399 latest | 2026-08-28 | 71a6399 | 7,458 B | A | view · diff |
| git:20260820.d8473ad | 2026-08-20 | d8473ad | 7,607 B | A | view · diff |
| git:20260811.925e30f | 2026-08-11 | 925e30f | 7,607 B | A | view · diff |
| git:20260802.46e0a37 | 2026-08-02 | 46e0a37 | 7,495 B | A | view · diff |
| git:20260726.3eac536 | 2026-07-26 | 3eac536 | 7,482 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 (7458 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
lugassawan/swe-workbench · 3 stars · license MIT · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ywyobvk3z54d2y7d GET https://markdownregistry.com/api/v1/resolve?ref=lugassawan/swe-workbench/workflow-delegated-implementation GET https://markdownregistry.com/api/v1/blob/ffc0d0b30efb7e8c4ad251db9121e4a77828ac5877c523d327a0f920ef2ec007
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.