pn-loop

pn-loop is a skill for Claude Code, Codex from perniemann/pnCore. It costs 46 tokens per session (798 once invoked), scanned A, original, MIT.

A workflow that repeats a task and its verification command until the command succeeds. Verification might be a test, build, migration check, or other clearly defined pass condition.

In plain words
What is it for?
Use it to fix CI, get tests passing, complete migrations, or build a project until the chosen check exits successfully.
Why use it?
It keeps work going through failures instead of stopping after the first unsuccessful attempt or assuming the result is correct.

Skill for Claude CodeCodex

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

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 skills/perniemann/pncore/pn-loop
Any agent
npx skills add perniemann/pnCore --skill pn-loop
Clone the repo
git clone --depth 1 https://github.com/perniemann/pnCore

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 pn-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/perniemann/pncore/pn-loop.svg)](https://agentmods.dev/skills/perniemann/pncore/pn-loop)
Your own site
<a href="https://agentmods.dev/skills/perniemann/pncore/pn-loop"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 798 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 5.1 $0.00046 $0.00798
Opus 5 $0.00023 $0.00399
Sonnet 5 $0.00009 $0.00160
Haiku 4.5 $0.00005 $0.00080

Measured 2d ago against content hash 6cd288969c63, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

pn-loop 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.

packages/pn-core-mcp/content/skills/ci/pn-loop/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Loop

Overview

pn-loop runs an autonomous fix-until-pass cycle: work on the task, run verification, if it fails then fix and repeat. Completion is determined by verification command output, not by self-declared phrases. This aligns with pn-verification-before-completion: evidence before claims.

Inspired by the Ralph Wiggum technique but uses pnCore's verification-first approach: the loop ends when the verification command succeeds, not when the agent says "done."

When to use

  • Fix CI until green — Run CI/tests each turn; fix failures; repeat until pass.
  • Get tests passing — Run test command; fix failures; repeat until 0 failures.
  • Complete a migration — Run migration verification; fix issues; repeat until clean.
  • Build until success — Run build; fix errors; repeat until exit 0.
  • Any task with clear, runnable verification and a known success condition.

Not a good fit: Tasks needing human judgment, ambiguous goals, or no single verification command.

Workflow

  1. Define verification — Identify the command that proves success (e.g. npm test, npm run build, npx playwright test). State the expected output (e.g. "0 failures", "exit 0").

  2. Work — Implement or fix the task using relevant skills (pn-ci-fix, pn-tdd, pn-systematic-debugging, etc.).

  3. Verify — Run the verification command. Read full output and exit code.

  4. Decide

    • Pass: Verification output confirms success → task complete. Use pn-verification-before-completion: state the evidence, then claim done.
    • Fail: Verification shows failures → fix the issues, then go to step 3. Do not claim done.
  5. Safety limit — If a max iteration count is specified (e.g. 10), stop after that many verification attempts and report remaining issues. Do not loop indefinitely without a cap when the user expects one.

Key principles

  • Verification is the gate — The loop ends when the verification command succeeds. No shortcuts.
  • Re-run verification each turn — Fresh run, full output. No "should pass" or extrapolation.
  • Fix, then verify again — After each fix, run the verification command again before claiming anything.
  • Evidence before completion — Follow pn-verification-before-completion: run the command, read output, then state result.

Read the full file on GitHub · 68 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 · 68 lines · 46 tokens per session scan A 6cd288969c63

Subscribe to this mod's changes

pn-loop is a skill published in the GitHub repository perniemann/pnCore (0 stars, last pushed 2d ago), licensed MIT. It adds 46 tokens to every session and 798 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 2026-09-03.

Related

Other skills, from other repositories

t-800-factory-scaffold

Procedural checklist CREATE артефактов T-800 через factory (не ad-hoc Write в agents/skills/commands/rules/hooks). Use when /t800-start, factory CREATE, factory-brief, или «собери агента/skill/command». Do NOT use when /t800-fix PATCH, обычный код без Cursor-артефактов, или обучение новичка (→ Task t-800-operator).

Khar-AG/t-800-agent · 100 tokens

t-800-command-chains

Как читать и обновлять machine-readable commandchains T-800 и не плодить orphan commands/agents. Use when правка commands/, registry, graph команд↔агенты, или после добавления /t800- команды. Do NOT use when soft prose orchestration в agent body без JSON, plugin-audit полный отчёт (→ t-800-plugin-auditor), или product…

Khar-AG/t-800-agent · 91 tokens

t-800-fix-pack

Структура fix-pack и constraints factory PATCH для /t800-fix. Use when правка существующего артефакта, fix-packs/ .md, audit→fixpack, или mode PATCH. Do NOT use when полный CREATE /t800-start, Loop report-only (/t800-loop), или doctor/plugin-audit без PATCH.

Khar-AG/t-800-agent · 79 tokens

t-800-plugin-sync

Procedural install/sync T-800 в /.cursor/plugins/local с CONTENTDRIFT --check и обязательным Reload Window. Use when install-plugin, sync --check, CONTENTDRIFT, stale marketplace pin, или «плагин не обновился». Do NOT use when KB sync-docs (/t-800-sync → t-800-knowledge-base), factory CREATE артефактов, или MIR в…

Khar-AG/t-800-agent · 98 tokens

t-800-run-gates

Какие machine gates гонять перед «готово» в прогоне T-800 (rungate, frontmatter, doctor/audit по режиму). Use when перед сдачей CREATE/PATCH, STATE Gates, strict-create, или exit code gates. Do NOT use when проектирование промпта (prompt-craft), обучение новичка, или cloud conversation hooks как sole-gate (P1).

Khar-AG/t-800-agent · 89 tokens

t-800-knowledge-base

Карта KB плагина T-800 Agent для ОБНОВЛЕНИЯ базы знаний (sync, CHANGELOG). НЕ вызывать для ответов пользователю — для этого Task(t-800-operator).

Khar-AG/t-800-agent · 50 tokens