agentic-loop-engineering-kit: Skill for Cursor

.cursor/skills/agentic-loop/SKILL.md

agentic-loop-runbook is a skill for Cursor from pallerana/agentic-loop-engineering-kit. It costs 45 tokens per session (3,084 once invoked), scanned A, original, Apache-2.0.

A runbook for a phased workflow that investigates, plans, implements, tests, and reviews changes in a monorepo, a repository containing multiple related projects. It uses profiles, Plan mode, and human approval gates across phases 0 through 9.

In plain words
What is it for?
Use it to start a profile-based engineering or incident workflow, investigate pull requests, control implementation and deployment phases, and route failures for human decisions.
Why use it?
It limits how far the agent proceeds without approval and prevents automatic retries or production pushes. The default mode stops after initial investigation and planning.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is pallerana/agentic-loop-engineering-kit's own configuration. It tells Cursor how to work on agentic-loop-engineering-kit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentic-loop-engineering-kit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pallerana/agentic-loop-engineering-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/pallerana/agentic-loop-engineering-kit/main/.cursor/skills/agentic-loop/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/pallerana/agentic-loop-engineering-kit

Made for: Cursor.

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 agentic-loop-runbook

README.md
[![agentmods](https://agentmods.dev/badge/skills/pallerana/agentic-loop-engineering-kit/agentic-loop.svg)](https://agentmods.dev/skills/pallerana/agentic-loop-engineering-kit/agentic-loop)
Your own site
<a href="https://agentmods.dev/skills/pallerana/agentic-loop-engineering-kit/agentic-loop"><img src="https://agentmods.dev/badge/skills/pallerana/agentic-loop-engineering-kit/agentic-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,084 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.
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 $0.00045 $0.03084
Opus 5 $0.00023 $0.01542
Sonnet 5 $0.00009 $0.00617
Haiku 4.5 $0.00005 $0.00308

Measured 6d ago against content hash 0def4d54fbff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agentic-loop-runbook 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 6d ago.

The scan reads SKILL.md. This mod also ships 9 executable files (scripts/act-run.sh, scripts/apply_loop_learning.py, scripts/apply-loop-learning.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.cursor/skills/agentic-loop/SKILL.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic Loop Engineering Kit Runbook

Profile-driven loop for your monorepo Java services and ops incidents.

Catalog: loop-kit/LOOP.md · Gates: GATES.md · Wiki: cell-health-agent-loop.md

Hard rules (plan-mode-first)

  1. Never start in Agent mode — call SwitchMode(plan) at loop start
  2. Default mode L1 — Phase 0→2 only unless --mode L2 or --mode L3-push and user explicitly approves in chat
  3. Stop after Phase 2 until user says e.g. "proceed with implementation" or approves --mode L2/L3-push
  4. Failure Router recommends only — do not auto-re-dispatch; present classification and wait for human
  5. Phase 4 scripts run only after human approves Phase 3
  6. L3-push push/CI babysit only after user explicitly approves ship

Invocation

/agentic-loop --profile <id> [options] [target]
 [options] [target]   # alias → --profile cell-health

PR review targets (--pr or URL)

Input Behavior
--pr <n> Phase 5 PR review; repo from profile / --repo
https://github.com/{owner}/{repo}/pull/{n} Parse URL → Phase 5; infer profile/repo from workspace folder name
--pr <n> + URL URL wins if numbers differ; warn in Functional Context
--pr or URL without --phase Jump to Phase 5 (skip 0–4 unless full loop requested)

Default for PR review: --mode L1 (report-only per pr-code-review.mdc).

Profile inference from repo name: your-service-* → matching profile (cellrouter, cellassignments, etc.); infra/--repo infra/.

# Java PR — auto-detects java-only
/agentic-loop --profile cellrouter --mode L1 --pr 78

# URL only — auto-resolves repo + PR number
/agentic-loop --mode L1 https://github.com/<org>/your-service-api/pull/123

# Infra-only PR
/agentic-loop --profile springboot-default --repo infra/ --mode L1 --pr <n>

# Thread hygiene after green CI (Phase 7 — not full review)
/agentic-loop --profile cell-health --phase 7 --pr 2

Read the full file on GitHub · 248 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. 6d ago First seen · 248 lines · 45 tokens per session scan A 0def4d54fbff

Subscribe to this mod's changes

agentic-loop-runbook is a skill published in the GitHub repository pallerana/agentic-loop-engineering-kit (4 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 3,084 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens