paradigmxyzparadigmxyz/centaur/.agents/skills/harness-development/SKILL.md

harness-development

Skill1.4k starsChanged 2 months agoLicence not identifiedView on GitHub

Add, modify, or debug Centaur harness-server backends in crates/harness-server. Use when adding a new harness CLI, changing how Codex, Claude Code, Amp, Pi, Nanocodex, or Hermes output is normalized, or investigating harness streaming, interrupt, resume, model, or reasoning-effort behavior.

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 1 is distinctive, and 6 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.

The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Oct 28, 2026claude-code-plugins.github.paradigmxyz.centaur: init at 2026.10.23 — sudosubin/agents.nix0 reactions
Oct 28, 2026claude-code-marketplaces.github.paradigmxyz.centaur: init at 2026.10.23 — sudosubin/agents.nix0 reactions
Oct 23, 2026codex-marketplaces.github.paradigmxyz.centaur: 2026.10.16 → 2026.10.23 — sudosubin/agents.nix0 reactions
Oct 23, 2026codex-plugins.github.paradigmxyz.centaur: 2026.10.16 → 2026.10.23 — sudosubin/agents.nix0 reactions
Oct 16, 2026codex-marketplaces.github.paradigmxyz.centaur: 2026.10.9 → 2026.10.16 — sudosubin/agents.nix0 reactions

21 more on GitHub

Oct 16, 2026codex-plugins.github.paradigmxyz.centaur: 2026.10.9 → 2026.10.16 — sudosubin/agents.nix0 reactions
Oct 14, 2026codex-marketplaces.github.paradigmxyz.centaur: 2026.10.2 → 2026.10.9 — sudosubin/agents.nix0 reactions
Oct 13, 2026codex-plugins.github.paradigmxyz.centaur: 2026.10.2 → 2026.10.9 — sudosubin/agents.nix0 reactions
Oct 4, 2026codex-plugins.github.paradigmxyz.centaur: init at 2026.10.2 — sudosubin/agents.nix0 reactions
Oct 4, 2026codex-marketplaces.github.paradigmxyz.centaur: init at 2026.10.2 — sudosubin/agents.nix0 reactions
Sep 26, 2026Broken links report — tortuvshin/open-apps0 reactions
Sep 18, 2026Accept memory-only Curator inference schema — bradwmorris/centaur0 reactions
Sep 7, 2026fix(auth): preserve bot origin credentials — phylaxsystems/centaur0 reactions · 3 comments
Sep 3, 2026feat(websearch): abstract over the backend; Tako is the default — jed326/centaur0 reactions
Aug 31, 2026fix(slack): enforce channel exclusions — phylaxsystems/centaur0 reactions · 2 comments
Aug 29, 2026Cron runs no longer re-schedule themselves from recurring prompt language (port centaur#1479) — NousResearch/hermes-agent0 reactions · 1 comment
Aug 29, 2026Mid-turn messages now get read receipts on every adapter (salvage #72503, scouted via centaur#1519) — NousResearch/hermes-agent0 reactions · 1 comment
Aug 16, 2026Epic: Organizational memory 2.0 — auto-capture, consolidation, graph recall (outsource the memory layer) — serrrfirat/bottega0 reactions · 2 comments
Aug 7, 2026feat(slack): surface emoji reactions in thread context (port of centaur#1264) — NousResearch/hermes-agent0 reactions · 3 comments
Aug 2, 2026feat: add provisioning adapter boundary — wcordelo/opentag0 reactions
Aug 2, 2026feat: add memory deletion adapter boundary — wcordelo/opentag0 reactions
Aug 2, 2026feat: add identity custody adapter boundary — wcordelo/opentag0 reactions
Jun 2, 2026WIP: docs(centaur): plan for a centaur deployment — ObolNetwork/obol-stack0 reactions · 1 comment
May 25, 2026Remove platform-level Modal credentials and make Modal BYO workspace-scoped only — sseshachala/conductai0 reactions
May 21, 2026[codex] Add Centaur to catalog — Picrew/awesome-agent-harness0 reactions · 1 comment
May 13, 2026feat(ai): add declarative lightweight agentic isolation — F1bonacc1/process-compose0 reactions · 8 comments

In this repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- services/AGENTS.mdAGENTS.md
- auth-failure-log-triageSkill
- centaur-console-permissionsSkill
- centaur-observabilitySkill
- company-contextSkill
- creating-toolsSkill
- docsendSkill
- e2e-testingSkill
- gcloudSkill
- open-prSkill
- prompt-iterationSkill
- qaSkill
- tool-health-smokeSkill

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

What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free