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 skills add MauricioPerera/KDD --skill delegar-pool-ccddgit clone --depth 1 https://github.com/MauricioPerera/KDDWrote 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.
[](https://agentmods.dev/skills/mauricioperera/kdd/delegar-pool-ccdd)<a href="https://agentmods.dev/skills/mauricioperera/kdd/delegar-pool-ccdd"><img src="https://agentmods.dev/badge/skills/mauricioperera/kdd/delegar-pool-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.
<a href="https://agentmods.dev/skills/mauricioperera/kdd/delegar-pool-ccdd"><img src="https://agentmods.dev/badge/skills/mauricioperera/kdd/delegar-pool-ccdd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 11 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.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00127 | $0.01555 |
| Opus 5.5 | $0.00051 | $0.00622 |
| Sonnet 5.5 | $0.00025 | $0.00311 |
| Haiku 4.5 | $0.00013 | $0.00155 |
Grade A, and why
delegar-pool-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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegar UNA tarea a pool exec con CCDD gate
Capa mínima sobre delegar-pool (mecánica de
lanzamiento/logs/anti-riesgo, agnóstica a la tarea) + 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 el flujo de delegar UNA tarea suelta a pool y agrega lo
verificado en vivo (2026-07-26, Python y Rust) que es específico de pool
como implementador.
Rol (inviolable)
- Yo NO implemento. Interpreto el pedido, lo traduzco a un TASK-CONTRACT
con tests congelados, delego a
pool exec --unsafe-auto-allowvíadelegar-pool, y verifico el resultado yo mismo (nunca me fío del exit code ni del resumen final depool). - Recibir → contrato + tests → un solo comando de delegación → verificar → reportar → pedir la siguiente decisión.
Cómo delegar
- Redactar el TASK-CONTRACT (formato
kdd-okf-ccdd-hybrid: front-matter + 7 secciones) y los property-tests congelados en el mismo turno, ANTES de invocarpool. - Validar el contrato con
lint_task_contract(contract_text, test_code)hasta{"ok": true}— corregir yo el contrato, no delegarle eso apool. - Hashear (
sha256) el archivo de tests congelado y guardarlo. Crear en disco el target (stub vacío o implementación previa con bug, según el caso) y el archivo de tests ANTES de invocarpool. - Delegar con el comando base de
delegar-pool(--unsafe-auto-allowSIEMPRE,-d <dir>apuntando exactamente al directorio de la tarea — doble-chequear esa ruta, un-dmal apuntado escribe en el lugar equivocado sin aviso). El prompt le pide correr eltest_commandprimero (no asumir que pasa) y iterar SOLO sobre el target si falla. - Verificar yo mismo: re-hashear los tests (deben ser idénticos), correr el
test_commandde forma independiente, y si el repo tiene gate CCDD real corrermeasure_complexity+check_signaturesobre el código final (Python vía AST nativo, Rust/otros vía tree-sitter conlanguage: <lang>en la llamada).
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.
- 2mo ago First seen · 95 lines · 127 tokens per session scan A fa78bdcfb71f
delegar-pool-ccdd is a skill published in the GitHub repository MauricioPerera/KDD (11 stars, last pushed today), licensed MIT. It adds 127 tokens to every session and 1,555 once invoked, about $0.0005 per session on Opus 5.5. 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 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.…
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.
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.
anchor-prior-test
Empirically test whether a candidate term qualifies as a semantic anchor by probing how densely it sits in LLM training data — across several model tiers in a clean room — before proposing it. Use when triaging an anchor proposal, deciding anchor vs contract, or vetting a rename. Produces a verdict against the four…
linked-intent-dev
Guide for linked-intent development (LID). Consult for ALL code changes. Walks changes through a mode-aware six-phase workflow (HLD → LLD → EARS → intent-narrowing edge audit → tests-first → code) with mandatory stops between each phase. Bugs walk the arrow like any other change — no short-circuit. Enforces cascade…
bidirectional-differential
Audit coherence across an arrow of intent by running two parallel fresh Claude sessions — one reconstructs code from a single EARS, the other reconstructs the EARS from stripped code — then classifies the drift between them. Use when the user invokes /differential-audit, asks to audit EARS-to-code drift for a feature…