delegar-glm-ccdd

delegar-glm-ccdd is a skill for Claude Code, Codex from MauricioPerera/KDD. It costs 121 tokens per session (1,223 once invoked), scanned A, original, MIT.

A task delegator that sends one specific coding job to the cloud version of GLM-5.2. It checks the result against the real project files and, when requested, uses the CCDD quality gate.

In plain words
What is it for?
Use it to implement, fix, or extend one function or other focused task with GLM, then validate the result with tests or CCDD checks.
Why use it?
It removes the need to implement a small change yourself while still requiring an independent check of the agent's work. The delegated task runs in a temporary workspace rather than directly against the real repository.

Skill for Claude CodeCodex

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

Good fit Use it to implement, fix, or extend one function or other focused task with GLM, then validate the result with tests or CCDD checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mauricioperera/kdd/delegar-glm-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 delegar-glm-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 delegar-glm-ccdd

README.md
[![agentmods](https://agentmods.dev/badge/skills/mauricioperera/kdd/delegar-glm-ccdd/github.svg)](https://agentmods.dev/skills/mauricioperera/kdd/delegar-glm-ccdd)
Your own site
<a href="https://agentmods.dev/skills/mauricioperera/kdd/delegar-glm-ccdd"><img src="https://agentmods.dev/badge/skills/mauricioperera/kdd/delegar-glm-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 delegar-glm-ccdd

Your own site · 80×15
<a href="https://agentmods.dev/skills/mauricioperera/kdd/delegar-glm-ccdd"><img src="https://agentmods.dev/badge/skills/mauricioperera/kdd/delegar-glm-ccdd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,223 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 warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 8
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 15
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 $0.00121 $0.01223
Opus 5 $0.00060 $0.00611
Sonnet 5 $0.00024 $0.00245
Haiku 4.5 $0.00012 $0.00122

Measured 12d ago against content hash 587e9f5604b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

delegar-glm-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/delegar-glm-ccdd/SKILL.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Delegar UNA tarea a glm-5.2:cloud con CCDD gate

Capa mínima sobre delegar-ollama (mecánica de lanzamiento/probe/anti-cuelgue, agnóstica al modelo) + el contrato CCDD definido en kdd-okf-ccdd-hybrid (7 secciones + frontmatter, si el repo usa KDD). Esta skill NO reescribe esos dos — solo fija model=glm-5.2:cloud y agrega lo específico de delegar UNA tarea suelta.

Rol (inviolable)

  • Yo NO implemento. Interpreto el pedido, lo traduzco a una instrucción clara, delego a glm-5.2:cloud vía delegar-ollama, y verifico el resultado yo mismo (nunca me fío del reporte de glm).
  • Recibir → traducir → un solo comando de delegación → reportar → pedir la siguiente decisión. No cuestionar de más ni re-validar enfoque salvo que el usuario lo pida.

Cómo delegar

Usá el comando base y el probe de delegar-ollama con <MODEL>=glm-5.2:cloud. Si la tarea usa CCDD: contrato con las 7 secciones (ver kdd-okf-ccdd-hybrid) + property-tests congelados, validar con lint_task_contract y correr run_integration_gate hasta PASS sobre los archivos REALES del repo. Nunca run_ephemeral_agent apuntando al repo real: corre en un sandbox tempdir que VACÍA el directorio y puede destruir archivos.

Lecciones específicas de GLM (no de la mecánica de Ollama, ver delegar-ollama para esa)

  • GLM copia el REGISTRO del prompt, no el del repo (verificado 2026-07-04): un prompt en voseo produjo docs en voseo dentro de un repo en tuteo, aunque el prompt pedía "tono consistente con el README". Si el registro importa, decilo EXPLÍCITO con ejemplo ("tuteo: 'explora', no 'explorá'") o asumí el retoque al integrar.
  • El gate lo puedo correr YO al verificar (verificado 2026-07-04): si tengo el MCP ccdd-complexity en MI sesión, es más barato dar a GLM MCP vacío + hecho verificable por suite/comandos, y correr yo lint_task_contract sobre el entregable final. Gate-en-GLM solo cuando GLM deba ITERAR contra el gate (funciones nuevas complejas), no para validar un artefacto terminado.
  • Tareas de docs/texto → hecho por greps de presencia Y ausencia (verificado 2026-07-04): grep -n "<clave>" <files> (hit obligatorio) + grep -rn "<prohibido>" <files> || echo SIN_MENCIONES + suite verde. GLM pega la salida real; yo re-corro los mismos greps.

Read the full file on GitHub · 41 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 · 41 lines · 121 tokens per session scan A 587e9f5604b3

Subscribe to this mod's changes

delegar-glm-ccdd is a skill published in the GitHub repository MauricioPerera/KDD (8 stars, last pushed 3d ago), licensed MIT. It adds 121 tokens to every session and 1,223 once invoked, about $0.0006 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

crit-cli

Use when an agent needs to author or reply to crit inline comments programmatically (including multi-agent workflows commenting on shared code/plans/docs/proposals), publish or unpublish a crit review with crit share, sync a crit review to or from a GitHub PR or GitLab MR, or read/interpret a crit review JSON file.…

tomasz-tomczyk/crit · 110 tokens

crit-story

Author a crit story and continue the interactive review loop only when the user explicitly invokes crit-story or directly asks you to generate a crit story. Do not infer this skill from generic review, PR, or diff-review requests.

tomasz-tomczyk/crit · 47 tokens

crit

Review code changes, a plan, a live page (running dev server), or a local HTML file with Crit inline comments and structured human feedback. Use only when the user explicitly invokes /crit or directly asks to use Crit; a generic review request does not count.

tomasz-tomczyk/crit · 55 tokens

trio-omnigent

Run the Cursor-backed Omnigent Trio loop from the current Claude/Codex UI session when the user explicitly says “Trio Omnigent”, “Omnigent Trio”, or invokes /trio-omnigent. Do not use for an ordinary native Trio request.

albiol2004/trio-agent-loop · 61 tokens

trio-bridge

Suggest background Trio work by scanning a project and writing deduplicated proposal cards into proposals/.

albiol2004/trio-agent-loop · 23 tokens

research-a-evolve

Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and ...

GrayCodeAI/starling · 38 tokens