@dev-core-busy

Creator · dev-core-busy

Last updated · Aug 24, 2026

code-delegate

REVIEW · 59Registry indexed

>-

OpenAgentSkill Trust Score
59/100

Do not auto-install

Quality60/100
Audit74/100
Stars23
Verified installs0

Install targets

Codex install prompt

Install the "code-delegate" agent skill from https://github.com/dev-core-busy/jarvis/tree/master/.claude/skills/code-delegate. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: >- After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {"event_id":"install_<unique-id>","skill_slug":"dev-core-busy-code-delegate","task":"Install code-delegate","agent":"codex","outcome":"success","install_used":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.

Supply asset profile

Coding and developer agents

Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills.

Browse track

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agent fit

Claude Code + CLI + Codex

Codex, Claude Code, Cursor, CLI, or custom agents.

Install

Ready

npx skills add dev-core-busy/jarvis --skill code-delegate

Maintenance

fresh

Pushed today

Risk

Needs review

Dependency or permission surface needs review

GitHub quality

23

60/100 Quality · 67/100 Trust

Coverage tags

CodingCoding agentscoding-agentsagent-skill

Review notes

Dependency or permission surface needs review · Permission surface may require sandboxing

Agent adoption scorecard

Trust, audit, and install readiness at a glance

These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.

Quality

Promising
60

Useful candidate, but compare it with alternatives before adopting.

Trust

Do not auto-install
59

Trust Score v5 found insufficient evidence for agent installation. Treat this as discovery material, not an executable recommendation.

Audit

Needs review
74

A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.

OpenAgentSkill Trust Score v5

Human review before install

Choose a stronger alternative or inspect the source manually before any install attempt.

CodexClaude CodeCursorOpenAgentSkill CLI

Stars

23 GitHub stars

Repo activity

23 stars, 7 forks

Maintenance

Pushed today

License

Apache-2.0

Install

npx skills add dev-core-busy/jarvis --skill code-delegate

Install safety

standard package or runtime install path

Permission surface

secrets or environment access, shell or command execution

Agent outcomes

No agent outcome data yet

Docs

Usable metadata, review docs

Risk summary

Review before production

  • Low GitHub adoption signal
  • Quality score needs review
  • Permission surface needs review: secrets or environment access, shell or command execution
  • GitHub adoption: 23 GitHub stars

Install readiness

Install path available

  • Install path is available
  • Repository evidence is available
  • License is declared
  • No Agent Proven outcome evidence yet

Agent-readable metadata

Machine-readable decision data for this skill.

Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.

View technical data+

Suited tasks

  • Coding agents workflows
  • Claude Code teams
  • builders willing to evaluate younger projects
  • Inspect source files

Suited agents

CodexClaude CodeCursorOpenAgentSkill CLICLI

Install decision

Command
npx skills add dev-core-busy/jarvis --skill code-delegate
Policy
block
Human review
yes

Trust and risk

Trust
59/100
Audit
74/100
Risk level
Needs review

Outcome loop

Endpoint
/api/agent/outcome
Event ID
resolve
Outcomes
5

Install command

npx skills add dev-core-busy/jarvis --skill code-delegate

Do not use when

  • teams that need a vendor-supported SLA
  • production agents without a repository review
  • Low GitHub adoption signal
  • High-risk permission hints: Shell or command execution, Secrets or environment access
  • Dependency or permission surface needs review

Agent safety v2

34/100 · Avoid automatic install

Blocked for auto-installblock

This skill should not be selected by an agent without explicit human security review.

Do not auto-install. Inspect the source, dependencies, and permission surface first.

Resolve via API

high

Shell or command execution

Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.

medium

Network access

Skill likely fetches remote pages, APIs, repositories, or external services.

medium

Filesystem access

Skill may read or write project files, documents, generated artifacts, or local workspace state.

high

Secrets or environment access

Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.

  • High-risk permission hints: Shell or command execution, Secrets or environment access
  • Dependency or permission surface needs review

Agent resolve plan

Let an agent verify fit before installing.

The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.

Open text plan

Agent should check

  • Task fit and alternatives from Resolve API.
  • Audit score, trust score, and safety policy warnings.
  • Install target compatibility for Codex, Claude Code, Cursor, or CLI.

Copy prompt

Task: Use code-delegate in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20code-delegate%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/dev-core-busy-code-delegate/install
Install command: npx skills add dev-core-busy/jarvis --skill code-delegate
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.

Agent handoff

Give an agent the install path, not another directory page.

Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.

Open install API

Agent prompt

Use code-delegate for this task. Review https://www.openagentskill.com/api/skills/dev-core-busy-code-delegate/install, then install with: npx skills add dev-core-busy/jarvis --skill code-delegate

Registry metadata

Agent-readable profile for automatic skill selection.

This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.

Open manifest

Agent fit

61/100

Coding agents

Platforms

Claude Code

Audit report

Needs review · 74/100

A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.

View audit reportView eval report

Agent decision cockpit

Fallback candidate for Coding agents

Prototype with this skill first; keep a fallback candidate ready.

61
Readiness
Prototype
Stage

Role in stack

Fallback candidate

Primary fit

Coding agents

Trust label

Prototype first

Install path

Command ready

Use when

  • Coding agents workflows
  • Claude Code teams
  • builders willing to evaluate younger projects

Evidence

  • recent repository activity
  • install command or GitHub repo available
  • 60/100 quality profile
  • 5 OpenAgentSkill engagement events

review first

  • Low GitHub adoption signal

Implementation path

  1. 1Install it in a sandbox agent and run one Coding agents task end to end.
  2. 2Compare output quality, latency, and failure behavior against at least one alternative.
  3. 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.

Trust profile

Do not auto-install

Trust Score v5 found insufficient evidence for agent installation. Treat this as discovery material, not an executable recommendation.

59
OpenAgentSkill Trust Score

GitHub adoption

FIX

23 GitHub stars

Stars/forks activity

FIX

23 stars, 7 forks; issue activity unavailable in current metadata

Recent maintenance

PASS

Pushed today

License clarity

PASS

Apache-2.0

Good signals

  • AI review approved
  • Install path is available
  • Repository evidence is available
  • Recently maintained repository
  • Install command has no obvious high-risk pattern
  • Outcome loop is ready but needs first real agent run

Review before install

  • Low GitHub adoption signal
  • Quality score needs review
  • Permission surface needs review: secrets or environment access, shell or command execution
  • GitHub adoption: 23 GitHub stars
  • Stars/forks activity: 23 stars, 7 forks; issue activity unavailable in current metadata
  • Dependency/runtime risk: command execution surface, credential or environment access
  • Permission surface: secrets or environment access, shell or command execution
  • No real agent outcome reports yet
  • Human review required before unattended installation

Recommended action

Choose a stronger alternative or inspect the source manually before any install attempt.

Quality profile

Promising candidate for agent workflows

Useful candidate, but compare it with alternatives before adopting.

60
GitHub stars
23
Freshness
Today
Install ready
Yes
License
Apache-2.0
Review before install: Low GitHub adoption signal

Workflow fit

Use this skill in these scenarios

Workflow fit

Add it to a complete workflow

Alternative shortlist

Compare before you install

Similar skills that may fit this task.

Compare all

Overview

--- name: code-delegate description: >- Gibt eine eng umrissene Codeaufgabe an den Jarvis-Agenten ab und holt sie als geprueften Patch zurueck – spart Anthropic-Tokens bei mechanischer Breitenarbeit. Nutzen, wenn eine Aenderung VIEL Datei-Lesen und WENIG Beschreibung braucht und eine vorhandene Testdatei das Ergebnis beweist. ---

# Codearbeit an Jarvis abgeben

Jarvis rechnet auf kostenlosen Tokens. Diese Faehigkeit verschiebt **Lesen und Suchen** dorthin – nicht das Denken.

## Die Entscheidungsregel

**Delegiere nur, wenn die Beschreibung kurz und die Dateiarbeit breit ist.**

Musst du den Code erst lesen, um eine brauchbare Spezifikation zu schreiben, hast du die Ersparnis schon ausgegeben. Dann mach es selbst.

### Geeignet

| Klasse | Beispiel | |---|---| | Mechanische Breitenarbeit | „`-localhost` an alle x11vnc-Aufrufe" (16 Stellen), „Cache-Buster an 40 Skript-Tags" | | Eine kleine Aenderung mit vorhandenem Waechter | „Variable ergaenzen, `tests/test_branding_aliase.py` muss gruen bleiben" | | Zwei Stellen, die zusammenpassen muessen | Deklaration in `:root` UND `body`, Feld in `create_*` UND der Whitelist von `update_*` |

### NICHT geeignet – hier selbst arbeiten

- **Alles Konventionslastige.** CLAUDE.md hat ~167.000 Token. Ein 35B-Modell wendet die Regeln darin nicht zuverlaessig an. - **Alles Sicherheitsrelevante** (Gates, Sandbox, Rechte, Auth). - **Zustandswechsel.** „Aendere X, miss, mach rueckgaengig" ist reproduzierbar gescheitert (17 Schritte, kein Ergebnis). **Eine Delegation = ein Zielzustand.** Den Rueckbau macht der Server per `git checkout`. - **Alles ohne mechanischen Riegel.** Kein Test, der es beweist → nicht delegieren. Die Modellantwort allein ist kein Nachweis.

## Ablauf

```bash S=deploy/claude_subagent/delegiere.py # im Repo versioniert, nicht in .claude/

# 1. Auftrag schreiben (Datei, damit Anfuehrungszeichen nicht stoeren) cat > /tmp/auftrag.txt <<'EOF' In frontend/css/chat.css im :root-Block die Variable ergaenzen: --accent-soft: color-mix(in srgb, var(--accent) 20%, transparent); EOF

# 2. Abgeben -> gibt die Auftragskennung aus ID=$(python3 $S senden --spec-datei /tmp/auftrag.txt \ --dateien frontend/css/chat.css \ --riegel tests/test_branding_aliase.py)

# 3. Warten; bei Erfolg kommt der Patch auf stdout, der Bericht auf stderr python3 $S warten "$ID" > /tmp/patch.diff ```

## Die Abbruchregel – ausnahmslos

Der Server prueft **alles-oder-nichts** und liefert nur dann einen Patch: Patch nicht leer · nur die freigegebenen Dateien angefasst · Riegel gruen · Patch nicht gekuerzt.

Kommt **kein** Patch (Exitcode ≠ 0), dann **mach die Aufgabe selbst**. Nicht nachbessern lassen, nicht ein zweites Mal delegieren, nicht „fast richtig" uebernehmen. Ein zweiter Versuch kostet mehr als die Ersparnis.

Kommt ein Patch, **lies ihn**, bevor du ihn anwendest:

```bash git apply --check /tmp/patch.diff && git apply /tmp/patch.diff ```

Ein gruener Riegel beweist, dass die Aenderung *funktioniert* – nicht, dass sie zu den Projektkonventionen passt (Einrueckung, Spaltenausrichtung, Kommentare). Das ist deine Aufgabe und der Grund, warum der Patch klein sein muss.

## Was der Auftragstext enthalten muss

Der Agent kennt die Projektregeln **nicht**. Schreibe deshalb:

- **Was genau** wo hinein soll – woertlich, wenn es ein fester Text ist. - **Keine** Begruendung, keine Historie, kein „wie ueblich". - **Kein** „raeum dabei auf", „formatiere mit", „pruefe auch noch".

Zahlen aus der Antwort des Agenten sind **wertlos** – er zaehlt nachweislich falsch (drei von drei Probelaeufen). Verlass dich auf Patch und Riegel; beides rechnet der Server selbst.

## Voraussetzungen

Diese Datei ist bereits auf DIESE Installation ausgestellt – die beiden Befehle unten sind vollstaendig, es fehlt nur der Schluessel:

```bash printf '%s' 'HIER-DEINEN-SCHLUESSEL-EINSETZEN' > ~/.jarvis-csa-key printf '%s' 'https://191.100.144.1' > ~/.jarvis-csa-url chmod 600 ~/.jarvis-csa-key ```

- **Schluessel** in `JARVIS_CSA_KEY` oder `~/.jarvis-csa-key` – in Jarvis unter `https://191.100.144.1/claude` erzeugen. **Nie ins Repo.** - **Adresse** ist oben schon eingesetzt: `https://191.100.144.1`. (Ueber `JARVIS_CSA_URL` bzw. die Datei laesst sich der Client auch gegen eine andere Installation richten – eine feste Vorgabe im Code gibt es bewusst nicht.) - Der lokale Stand muss auf `origin/master` liegen und die Zieldateien duerfen keine ungespeicherten Aenderungen haben – der Client prueft beides und bricht sonst ab.

Laeuft gegen **jede** Jarvis-Installation, auch produktive. Der Riegel ist dort verfuegbar, weil der Arbeitsbereich frisch von `origin/master` geklont wird – ein `sparse-checkout` auf dem Server (der `tests/` in `/opt/jarvis` ausblendet) wirkt nur auf dessen eigene Arbeitskopie, nicht auf einen neuen Klon.

## Beiblatt: CLAUDE.md schlank halten

Die Ausschlussregel „nichts Konventionslastiges" oben haengt an der Groesse von CLAUDE.md – je dicker die Datei, desto weniger laesst sich abgeben. Ein paste-fertiger Auftrag zum Verschlanken steht in **`claude-md-diaet.md`** (Download im Bereich `https://191.100.144.1/claude`, Abschnitt „Anleitung"). Er ist eigenstaendig – kein Jarvis, keine Delegation – und wird ausdruecklich **nicht** delegiert: CLAUDE.md ist die Konvention selbst.

Technical details

Version
1.0.0
License
Apache-2.0
Last updated
Aug 24, 2026
Published
Aug 24, 2026

Decision snapshot

Fallback candidate

61
Ready
Prototype
Stage

recent repository activity

Audit

Install review

Install and adoption review

74
Needs review
Security
77/100
Maintenance
100/100
Install
92/100
Open full auditView eval report

Agent-proven evidence

Agent-proven evidence

Outcome reports after resolve, review, install, and one narrow run.

0
Proven
Needs first agent runAuto-install: review firstLast: Unknown
Success rate
Recent failure
Outcomes
0
Output quality
Failed
0
Not relevant
0
Installs
0
Risk blocked
0
Setup needed
0
Production
0

No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.

Install

Add to agent workflow

Free and open source. Review the report before installing into production agents.

Growth loop

Share kit

X

Scenario-led draft for code-delegate, ready for a manual X post.

Curator note
Before you hand an agent the next repo task, give it a repeatable starting point.

code-delegate: >-

23 stars

https://www.openagentskill.com/skills/dev-core-busy-code-delegate?ref=x
Open X draft
Optional reply with install command
Listing + install path for code-delegate:
https://www.openagentskill.com/skills/dev-core-busy-code-delegate?ref=x

Install: npx skills add dev-core-busy/jarvis --skill code-delegate

Listing source

Registry indexed

Claimable

This listing was indexed from public sources and is not marked official until a maintainer claim is approved.

Indexed by
OpenAgentSkill community index

Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.

Claim this skill

Owner claim

Claim this skill listing

This Registry indexed listing is attributed to dev-core-busy but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.

Creator backlink kit

Add the evidence badges to your README

Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.

[![Listed on OpenAgentSkill](https://www.openagentskill.com/api/badge/dev-core-busy-code-delegate?metric=listed&label=Listed)](https://www.openagentskill.com/skills/dev-core-busy-code-delegate)
[![OpenAgentSkill Trust](https://www.openagentskill.com/api/badge/dev-core-busy-code-delegate?metric=trust&label=Trust)](https://www.openagentskill.com/skills/dev-core-busy-code-delegate)
[![OpenAgentSkill Audit](https://www.openagentskill.com/api/badge/dev-core-busy-code-delegate?metric=audit&label=Audit)](https://www.openagentskill.com/skills/dev-core-busy-code-delegate/audit)
[![Agent Proven](https://www.openagentskill.com/api/badge/dev-core-busy-code-delegate?metric=proven&label=Agent%20Proven)](https://www.openagentskill.com/skills/dev-core-busy-code-delegate)

Author

D

dev-core-busy

@dev-core-busy

Platform fit

Health signals

GitHub stars
23
Quality score
32/100
Last GitHub push
Aug 24, 2026
Framework hints
Unknown
OpenAgentSkill views
5
Install copies
0
Outbound clicks
0

Community signal

Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.

Trust & safety

Do not auto-install

59
  • GitHub adoption23 GitHub starsFIX
  • Stars/forks activity23 stars, 7 forks; issue activity unavailable in current metadataFIX
  • Recent maintenancePushed todayPASS
  • License clarityApache-2.0PASS
  • README/SKILL.md completenessPublic metadata needs stronger README/SKILL.md contextINFO
  • Dependency/runtime riskcommand execution surface, credential or environment accessCHECK