pm-native-ccdd

pm-native-ccdd is a skill for Claude Code, Codex from MauricioPerera/KDD. It costs 254 tokens per session (2,506 once invoked), scanned A, original, MIT.

A project coordinator that writes a task contract and fixed tests before sending implementation to a temporary Claude sub-agent. It checks the result with the CCDD quality gate, which applies repeatable rules and tests.

In plain words
What is it for?
Use it to plan and delegate coding tasks to Claude sub-agents, run their tests and checks, retry failures, and report whether the work passes.
Why use it?
It separates planning, coding, and checking so the coordinator does not have to trust an agent's summary or inspect every change manually. It can use different Claude models for different kinds of work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to plan and delegate coding tasks to Claude sub-agents, run their tests and checks, retry failures, and report whether the work passes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mauricioperera/kdd/pm-native-ccdd
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.

Any agent
npx skills add MauricioPerera/KDD --skill pm-native-ccdd
Clone the repo
git clone --depth 1 https://github.com/MauricioPerera/KDD

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pm-native-ccdd

README.md
[![agentmods](https://agentmods.dev/badge/skills/mauricioperera/kdd/pm-native-ccdd/github.svg)](https://agentmods.dev/skills/mauricioperera/kdd/pm-native-ccdd)
Your own site
<a href="https://agentmods.dev/skills/mauricioperera/kdd/pm-native-ccdd"><img src="https://agentmods.dev/badge/skills/mauricioperera/kdd/pm-native-ccdd/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pm-native-ccdd

Your own site · 80×15
<a href="https://agentmods.dev/skills/mauricioperera/kdd/pm-native-ccdd"><img src="https://agentmods.dev/badge/skills/mauricioperera/kdd/pm-native-ccdd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 254 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,506 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00254 $0.02506
Opus 5 $0.00127 $0.01253
Sonnet 5 $0.00051 $0.00501
Haiku 4.5 $0.00025 $0.00251

Measured 12d ago against content hash 8c82cb4bddec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

pm-native-ccdd 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 12d 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.

skills/pm-native-ccdd/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PM nativo · Devs = sub-agentes de la app (Agent + model override) · QA = CCDD gate

Misma metodología CCDD que pm-glm-ccdd — contrato + tests congelados autorados ANTES de delegar, verify-by-artifact, política de reintentos, red-team del HECHO, suite 2x. Lo único que cambia es el mecanismo de delegación: en vez de ollama launch (GLM externo), el implementador es un sub-agente nativo vía la tool Agent.

Tiering (los cuatro tiers, nativos)

  • Triage → Haiku 4.5 (Agent, model:"haiku"): leer issue, clasificar, limpiar log, mapear tools MCP, detectar si ya está hecho. Cortá el pipeline aquí si no hay trabajo.
  • PM/oráculo → Sonnet 5 (model:"sonnet") por defecto; Opus solo para oráculos adversariales sin tropo conocido. Autora contrato + tests congelados + lint + baseline rojo.
  • Dev/implementador → Haiku 4.5 (model:"haiku"), escalá a model:"sonnet" una función puntual si Haiku falla el gate 2×.
  • Gate/verify → el orquestador (vos): corrés mcp__ccdd-complexity__* + re-corrés los tests.

Cómo invocar cada agente (native)

Triage / PM / Dev — tool Agent:

Agent({ subagent_type: "claude", model: "haiku"|"sonnet"|"opus",
        run_in_background: true, isolation: "worktree" (solo devs en paralelo),
        description: "<3-5 palabras>", prompt: "<spec autocontenida>" })
  • El resultado (texto final del agente) vuelve como tool result; el harness reporta subagent_tokens / tool_uses / duration_ms en la notificación → medición de costo exacta.
  • run_in_background: true para no bloquear (llega notificación al terminar).

Paralelismo sin colisión — isolation: "worktree":

  • Cada dev en su propio git worktree → NO necesitás declarar "archivos disjuntos" (lo resuelve el aislamiento). Auto-limpiado si no cambió. Coste ~200-500ms + disco por agente: úsalo SOLO cuando varios devs mutan archivos a la vez; para tareas secuenciales, omitilo.

Reintento tras FAIL — SendMessage al MISMO dev (conserva contexto):

SendMessage({ to: "<agentId>", summary: "gate FAIL: cyclomatic 12>10",
              ... "extraé helpers, no toques los tests, re-corré node --test" })
  • Más barato que un Agent nuevo: el dev ya tiene el contexto de la tarea; solo le pasás el feedback del gate. (En pm-glm-ccdd cada retry re-lanzaba GLM re-enviando toda la spec.)

Read the full file on GitHub · 114 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. 12d ago First seen · 114 lines · 254 tokens per session scan A 8c82cb4bddec

Subscribe to this mod's changes

pm-native-ccdd is a skill published in the GitHub repository MauricioPerera/KDD (8 stars, last pushed 3d ago), licensed MIT. It adds 254 tokens to every session and 2,506 once invoked, about $0.0013 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.

Related

Other skills, from other repositories