Run Iterative Coding Loops Safely
Long coding tasks often fail because tests, lint checks, or completion criteria are not retried consistently. This skill provides a bounded loop pattern for Claude, Codex, and Claude Code workflows.
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "iterative-runner" from https://skillstore.io/skills/barissozen-iterative-runner.md and its manifest at https://skillstore.io/api/skills/barissozen-iterative-runner/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Using "iterative-runner". Fix a failing unit test with a 10 iteration limit.
Expected outcome:
The agent describes each attempt, applies focused changes, reruns the test, and stops when the suite passes.
Using "iterative-runner". Implement a feature using TDD completion criteria.
Expected outcome:
The agent reports added tests, implementation changes, verification results, and a final completion marker.
Using "iterative-runner". Continue an overnight build until a bounded success condition.
Expected outcome:
The workflow records attempts, stops at the maximum iteration count, and lists blockers if success is not reached.
The main real risk is that the skill demonstrates repeated agent execution through shell commands, including one unbounded loop example. Most static findings are Markdown fence or inline-code false positives, and I found no prompt injection or data-exfiltration intent.
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
https://skillstore.io/skills/barissozen-iterative-runner/audits/10?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/barissozen-iterative-runner?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/barissozen-iterative-runner?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/barissozen-iterative-runner/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/barissozen-iterative-runner.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>BarisSozen. (2026). iterative-runner security audit report (audit version 10) [Author version unspecified]. Skillstore. https://skillstore.io/skills/barissozen-iterative-runner/audits/10@techreport{barissozen-barissozen-iterative-runner-2026,
author = {BarisSozen},
title = {iterative-runner security audit report (audit version 10)},
institution = {Skillstore},
year = {2026},
number = {10},
url = {https://skillstore.io/skills/barissozen-iterative-runner/audits/10},
note = {Author version unspecified}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "iterative-runner security audit report (audit version 10)"
version: "unspecified"
type: report
authors:
- name: "BarisSozen"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/barissozen-iterative-runner/audits/10"
identifiers:
- type: other
value: "skillstore:barissozen-iterative-runner:audit:10"
description: "Skillstore immutable audit report identifier"
Use the workflow to keep retrying fixes until tests pass or a bounded iteration limit is reached.
Run a controlled agent loop that attempts build repairs and reports blockers when the limit is reached.
Give teams a repeatable pattern for complex tasks that need several repair and verification cycles.
Use iterative-runner to fix the failing test. Stop when all tests pass. Use a maximum of 10 iterations.
Implement the requested feature. Treat all tests passing and no linter errors as completion. Output the completion marker only after verification.
Build the feature with TDD. First add a failing test, then implement, run checks, and revise within 25 iterations.
Use an iterative loop for this migration. Complete schema changes, tests, and documentation in phases. After 30 failed iterations, summarize blockers.
Author
BarisSozenLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
0519034dad657fb1f7706e0550e962beeda73fdf
Maintenance freshness
7/21/2026
Usage
6 downloads · 219 views
File structure
📄 SKILL.md
Audit AI Skills for Quality and Structure
Inconsistent skill structure makes reviews and packaging harder. This auditor checks metadata, content, resources, and decomposition signals with repeatable rules.
Design Apple-Inspired Interfaces
Modern product teams need consistent, polished UI guidance. This skill gives Claude, Codex, and Claude Code practical Apple-inspired rules for typography, color, spacing, components, motion, and UX review.
Validate Cross-Language Type Consistency
Cross-language type drift can cause precision loss and contract bugs. This skill guides Claude, Codex, and Claude Code through Rust, TypeScript, and PostgreSQL checks.
Validate System Integrations Before Deployment
Integration failures can block deployments through port conflicts, unavailable databases, or mismatched APIs. This skill provides a focused checklist for finding those problems early.
Track MEV Latency With Span Guidance
Latency issues in MEV systems are hard to isolate across calls and transaction stages. This skill guides span hierarchy, instrumentation, aggregation, and alert thresholds.
Avoid Drizzle ORM Migration Pitfalls
Drizzle ORM schema mistakes can break migrations and weaken type safety. This skill guides Claude, Codex, and Claude Code toward safer patterns.
Build Reliable Test Automation
by 89jobrien
Weak tests slow releases and hide regressions. This skill guides test strategy, TDD, automation, coverage review, and Playwright web checks.
Build Reliable Jest Tests
by C0ntr0lledCha0s
Jest projects often fail because tests, mocks, asynchronous behavior, and configuration are inconsistent. This skill provides focused patterns for dependable JavaScript, TypeScript, React, and Node.js testing.
Build Reliable Playwright Tests
by C0ntr0lledCha0s
Playwright test suites can become flaky, slow, and difficult to maintain. This skill provides practical patterns for locators, fixtures, page objects, debugging, mocking, and configuration.
Build Claude Code Agents
by C0ntr0lledCha0s
Creating reliable AI agents requires clear schemas, safe tools, and repeatable review steps. This skill guides agent design, validation, migration, and maintenance for Claude Code workflows.
Build Claude Code Agents
by Dami-Randle
Designing reliable Claude Code agents is hard without structure. This skill provides templates, validation rules, and examples for agent prompts, triggers, tools, and metadata.
Build Claude Code Slash Commands
by C0ntr0lledCha0s
Teams need repeatable AI workflows that are easy to invoke and review. This skill helps create, update, validate, and document Claude Code slash commands.