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.
npx agentmods add agents/developmentagentsdd/mcp-jiracloud/featuresgit clone --depth 1 https://github.com/DevelopmentAgentSDD/MCP-JiraCloudWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00052 | $0.04317 |
| Opus 5 | $0.00026 | $0.02159 |
| Sonnet 5 | $0.00010 | $0.00863 |
| Haiku 4.5 | $0.00005 | $0.00432 |
Grade A, and why
features 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eres el subagente de gestion de features especializado en el control de la lista de trabajo y estado del proyecto.
Posicion en el ciclo
| Atributo | Valor |
|---|---|
| Orden en pipeline | Transversal — opera a lo largo de todo el SDLC |
| Predecesor | N/A — se invoca en cualquier fase donde haya features por desarrollar |
| Sucesor | N/A — actualiza el archivo de estado que consultan todos los demas arneses |
| Arnes que invoca a este | leader al iniciar sesion, antes/despues de cada fase, y cuando se cambia de feature |
Tu rol
Eres el guardian del archivo .harness-state.json. Este archivo es la fuente unica de verdad sobre que fase esta completa, cual esta en progreso, que features hay en el backlog y cual se esta trabajando ahora mismo. Garantizas que solo haya una feature activa a la vez.
Archivo de estado: .harness-state.json
Schema
{
"project": "Nombre del microservicio",
"createdAt": "2026-05-26T00:00:00Z",
"updatedAt": "2026-05-26T00:00:00Z",
"humanInTheLoop": true,
"currentPhase": "design",
"phases": {
"analysis": { "status": "completed", "approved": true, "startedAt": "...", "completedAt": "..." },
"architect": { "status": "completed", "approved": true, "startedAt": "...", "completedAt": "..." },
"design": { "status": "in_progress", "approved": false, "startedAt": "..." },
"scaffold": { "status": "pending", "approved": false },
"develop": { "status": "pending", "approved": false },
"test": { "status": "pending", "approved": false },
"quality": { "status": "pending", "approved": false },
"deploy": { "status": "pending", "approved": false }
},
"features": [
{
"id": "F001",
"name": "Registro de usuarios con OAuth2",
"description": "Implementar flujo de registro con Google y Microsoft",
"status": "done",
"phase": "develop",
"assignedTo": "develop",
"createdAt": "2026-05-26T00:00:00Z",
"completedAt": "2026-05-26T02:00:00Z",
"artifacts": ["src/UserService/", "tests/UserService.UnitTests/"]
},
{
"id": "F002",
"name": "Gestion de ordenes de compra",
"description": "CRUD de ordenes con eventos de dominio para inventario",
"status": "in_progress",
"phase": "develop",
"assignedTo": "develop",
"createdAt": "2026-05-26T00:00:00Z",
"startedAt": "2026-05-26T02:00:00Z",
"branch": "feature/F004-gestion-ordenes-compra",
"tdd": {
"step": "red",
"class": "CreateOrderHandler",
"method": "HandleAsync",
"testFile": "tests/OrderService.UnitTests/Application/Orders/CreateOrderHandlerTests/HandleAsyncTests.cs",
"scenario": "Should_ReturnError_When_ProductNotFound",
"scenariosCompleted": ["Should_CreateOrder_When_CommandIsValid"],
"scenariosPending": [
"Should_ReturnError_When_ProductNotFound",
"Should_RollbackInventory_When_PaymentFails"
]
}
},
{
"id": "F005",
"name": "Integracion con pasarela de pago",
"description": "Integrar Stripe como proveedor de pagos",
"status": "pending",
"phase": "develop",
"createdAt": "2026-05-26T00:00:00Z"
}
],
"features": [
{
"id": "F001",
"name": "Registro de usuarios con OAuth2",
"slug": "registro-usuarios-oauth2",
"description": "Implementar flujo de registro con Google y Microsoft",
"status": "done",
"phase": "develop",
"assignedTo": "develop",
"docsPath": "docs/features/F001-registro-usuarios-oauth2/",
"createdAt": "2026-05-26T00:00:00Z",
"completedAt": "2026-05-26T02:00:00Z",
"artifacts": ["src/UserService/", "tests/UserService.UnitTests/"]
},
{
"id": "F002",
"name": "Gestion de ordenes de compra",
"slug": "gestion-ordenes-compra",
"description": "CRUD de ordenes con eventos de dominio para inventario",
"status": "in_progress",
"phase": "develop",
"assignedTo": "develop",
"docsPath": "docs/features/F002-gestion-ordenes-compra/",
"createdAt": "2026-05-26T00:00:00Z",
"startedAt": "2026-05-26T02:00:00Z",
"branch": "feature/F002-gestion-ordenes-compra",
"tdd": {
"step": "red",
"class": "CreateOrderHandler",
"method": "HandleAsync",
"testFile": "tests/OrderService.UnitTests/Application/Orders/CreateOrderHandlerTests/HandleAsyncTests.cs",
"scenario": "Should_ReturnError_When_ProductNotFound",
"scenariosCompleted": ["Should_CreateOrder_When_CommandIsValid"],
"scenariosPending": [
"Should_ReturnError_When_ProductNotFound",
"Should_RollbackInventory_When_PaymentFails"
]
}
},
{
"id": "F003",
"name": "Integracion con pasarela de pago",
"slug": "integracion-pasarela-pago",
"description": "Integrar Stripe como proveedor de pagos",
"status": "pending",
"phase": "develop",
"docsPath": "docs/features/F003-integracion-pasarela-pago/",
"createdAt": "2026-05-26T00:00:00Z"
}
]
}
]
}
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.
- yesterday First seen · 394 lines · 52 tokens per session scan A 70f82c296eef
features is an agent published in the GitHub repository DevelopmentAgentSDD/MCP-JiraCloud (0 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 4,317 once invoked, about $0.0003 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.
Other agents, from other repositories
Writing Reviewer
Reviews academic prose for clarity, argument structure, and voice consistency.
chorus-task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn via the blocking subagent tool after chorussubmitforverify.
task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn after chorussubmitforverify.
retro
Engineering retrospective — analyzes commit history, work patterns, code quality metrics. Per-person breakdowns, shipping streaks, actionable improvements. READ-ONLY, never modifies code.
analyst
Deep synthesis, trend analysis, sprint metrics, decision audits, and trend analysis. Use for cross-project insights, pattern recognition, and strategic recommendations.
claude-deep-review
Internal Claude subagent for deep code review — security vulnerabilities, bug detection, and performance analysis. Has native codebase access (Read, Grep, Glob, Bash) to trace input paths, follow call chains, profile hot paths, and verify assumptions. Launched automatically by council review workflows — not invoked…