paseo-slp-plugin
Supervisor-Lead-Peer roles for a team of Paseo coding agents, with opt-in Jev routing recorded as a receipt in shadow mode.
Overview
Paseo SLP organises a team of Paseo coding agents into Supervisor, Lead and Peer roles that separate kinds of judgment rather than form a chain of command. You give an SLP Lead a bounded objective (optionally through a Supervisor that observes and relays your decisions); the Lead frames acceptance, decomposes work, coordinates independent Peers with one writer per scope, selects review and returns a project verdict, while you keep control of intent, trade-offs and final acceptance. A repository desk stores durable assignments, briefs, a task queue, review obligations and evidence.
Per the list summary, it includes opt-in Jev routing that records a verifiable receipt in shadow mode and binds the decision when armed. The README excerpt does not describe which decisions are routed. It is documented in English and Vietnamese and advises using full SLP only when coordination is worth its overhead.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Which role or route should handle this piece of work?(inferred) | — |
How it works
- Start an SLP Lead with an objective.
- Lead decomposes and assigns work to Peers.
- Optional Jev routing records receipts in shadow mode, or binds when armed.
- Lead integrates and returns a verdict for human acceptance.
Strengths
- Clear role separation and durable work records.
- Shadow mode before letting Jev bind decisions.
Caveats
- Jev routing details only in the list summary.
- Overhead not worth it for small tasks.
At a glance
- Type
- Plugin
- Status
- beta
- Runtime
- Paseo plugin
- Has code
- yes
Use cases and integrations
How curated lists describe it
Supervisor, Lead and Peer roles for a team of Paseo coding agents, with opt-in Jev routing that records a verifiable receipt in shadow mode and binds it when armed. English and Vietnamese.
MrJev/awesome-jev
Frequently asked questions
What is SLP?
Supervisor, Lead and Peer roles for coordinating Paseo coding agents.
How is Jev used?
Opt-in routing that records receipts in shadow mode and binds when armed, per the list summary.
When should I not use it?
For small, bounded tasks one agent can handle.
Related projects
One skill and MCP server for Claude Code, Codex and Hermes where Jev gates large-model turns, routes models and guards Git steps.
MCP serverbetaPythonRuns Claude Code on Opus 5.5 with Jev re-picking reasoning effort after every tool batch, via per-message effort so the cache survives.
ProxybetaTypeScriptTerminal coding agent where an LLM reads, edits and runs code, and Jev makes a few optional side decisions.
ProjectbetaTypeScriptSelf-improving multi-platform agent harness with an optional Jev companion for typed judgments and per-session model routing.
ServicebetaTypeScriptMulti-agent Codex factory: Jev decides task shape, decomposition and routing, and failures are classified, not blindly retried.
ProjectprototypePythonClaude Code skill that splits work into PBIs for Codex, Antigravity or Claude sub-agents, using Jev for model choice and triage.
ProjectprototypePython