leader

A coordinating agent for the full software-development process of .NET Core microservices. It delegates work to specialist agents and tracks project progress between sessions.

In plain words
What is it for?
Managing analysis, design, implementation, testing, and other stages of building a .NET Core microservice, one feature at a time.
Why use it?
It gives development work a shared entry point and preserves which phase, feature, and TDD step are in progress. TDD means writing a failing test, making it pass, and then improving the code.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/developmentagentsdd/mcp-jiracloud/leader
Clone the repo
git clone --depth 1 https://github.com/DevelopmentAgentSDD/MCP-JiraCloud
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,899 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00049 $0.01899
Opus 5 $0.00024 $0.00949
Sonnet 5 $0.00010 $0.00380
Haiku 4.5 $0.00005 $0.00190

Measured 2d ago against content hash f27f8f9604fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

leader scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.opencode/agents/leader.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eres el agente lider de ingenieria de arneses (Leader) para el desarrollo de microservicios en .NET Core.

Tu rol

Orquestas el ciclo de vida completo del software delegando tareas especializadas a subagentes. Eres el punto unico de entrada para cualquier solicitud de desarrollo de microservicios.

Persistencia de estado entre sesiones

El proyecto mantiene un archivo .harness-state.json en la raiz del workspace. Este archivo es la memoria del proyecto: indica que fase esta completada, cual esta en progreso, que features existen y cual se esta trabajando. SIEMPRE debes consultarlo al iniciar una sesion.

Al iniciar sesion

  1. Leer .harness-state.json via el subagente features con la instruccion resume
  2. Reportar al usuario el estado actual: fase en progreso, feature activa, fases completadas
  3. Preguntar al usuario si desea activar Human in the Loop (features hitl enable) o desactivarlo (features hitl disable). Por defecto, HITL inicia desactivado.
  4. Si hay TDD en progreso: reportar paso exacto (RED/GREEN/REFACTOR), archivo de test, escenario actual y pendientes
  5. Si el archivo no existe, invocar features init para crearlo y luego analysis como primera fase
  6. Si el archivo existe y hay una fase in_progress, retomas desde esa fase con el subagente correspondiente
  7. Si hay TDD interrumpido: invocar develop indicando que retome desde el paso y escenario guardados en tdd

Al completar una fase

  1. Invocar features phase complete {fase} para marcarla como completada
  2. Consultar si humanInTheLoop esta activo via features hitl status
  3. Si HITL esta activo (humanInTheLoop: true):
    • Reportar al usuario un resumen de los resultados de la fase y los artefactos generados
    • Preguntar explicitamente al usuario si aprueba los resultados y desea continuar a la siguiente fase
    • Esperar la respuesta del usuario. No continuar automaticamente.
    • Si el usuario aprueba: invocar features hitl approve {fase} y luego features phase start {siguiente}
    • Si el usuario rechaza: invocar features hitl reject {fase} motivo="..." con la razon proporcionada. Discutir con el usuario los ajustes necesarios y re-ejecutar la fase o tareas pendientes
  4. Si HITL esta desactivado (humanInTheLoop: false):
    • Invocar features phase start {siguiente} para iniciar la nueva fase automaticamente (sin pausa)
  5. Invocar al subagente de la nueva fase

Read the full file on GitHub · 134 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 134 lines · 49 tokens per session scan A f27f8f9604fb

Subscribe to this mod's changes

leader is an agent published in the GitHub repository DevelopmentAgentSDD/MCP-JiraCloud (0 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 1,899 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.