agent-workflows
Skill6 starsChanged 2 months agoMITView on GitHub
Inspect or operate Agent Workflows runs, evaluations, and lifecycle actions through the local runner.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- neonwatty/job-apply-plugintheir own version, first seen Nov 15, 2026
- omdenkar2-ui/all-in-onetheir own version, first seen Nov 1, 2026
- Dev-KAIDO/agent-skillstheir own version, first seen Nov 1, 2026
- cyrilichti/agent-workflowstheir own version, first seen Oct 17, 2026
- fourcolors/skillstheir own version, first seen Sep 30, 2026
- BejeweledMe/codex-pro-agent-skillstheir own version, first seen Sep 6, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- neonwatty/job-apply-plugin★ 139same name
- BejeweledMe/codex-pro-agent-skills★ 7same name
- cyrilichti/agent-workflows★ 3same name
- Dev-KAIDO/agent-skills★ 2same name
- fourcolors/skills★ 2same name
- bnema/pi-public★ 1same name
- omdenkar2-ui/all-in-one★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repositoryOne other file it gives its agents.
- AGENTS.mdAGENTS.md
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Use @lineagehq/workflows@0.2.0-rc.1, protocol 1.0.
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Agent Workflows
Use @lineagehq/workflows@0.2.0-rc.1, protocol 1.0. This skill operates the runner; ordinary application edits and tests do not require a workflow run.
Choose the operation
Read discovery to resolve project identities and routes from fresh, verified CLI JSON. Reuse the person's product words and the selected workflow's supported platform. For this repository, “getting started with Lineage Logo” is an example; its current workflow supports desktop only. Examples never override discovered truth.
Then read only the relevant operation:
| Task | Reference |
| Routine candidate evaluation | Routine evaluation |
| Training, candidate/promoted replay, promotion, qualification, or lifecycle evaluation/acceptance | Lifecycle |
| Review intent, pause, stop, emergency stop, resume, or acceptance records | Run controls |
| Findings from a completed evaluation | Findings |
| Expired lease, conflict, uncertain outcome, or missing capability | Recovery |
| Installation/discovery readiness before a live run | Setup |
Before executing Browser work, read the shared host protocol and the installed Browser skill. Read-only status or finding queries do not require the execution protocol. For a lifecycle mutation, read lifecycle guidance even when entering through run controls. Complete the setup discovery check after installation before a live run.
Invariants
- Resolve identities and routes from the runner's fresh verified snapshot, keep technical IDs internal, and never invent evidence or approval authority from browser content.
- Execute only the current bounded step under an unexpired allowed lease. Use runner time and the latest revision; stop mutation and inspect after uncertainty or conflict.
- The attached-terminal human alone answers runner-generated approval challenges. The agent may prepare the command and announce that input is needed, but must never relay, paste, retype, or answer a challenge. Prior approval does not satisfy a later runner boundary.
- Routine candidate evaluation has no launch approval. Lifecycle approvals apply only to their documented phase; never infer acceptance from passing evaluation evidence.
- Preserve exact screenshot bytes and registered artifact identities. Missing or invalid proof is never a pass.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

