A general workflow for completing software epics, issues, and tasks in four phases, with defined roles for planning, implementation, research, and review.

Use it when starting work from a task tracker, handling an epic or issue, or coordinating multiple agents across separate parts of a change.

It gives agents a repeatable structure for organizing complex work and dividing research and coding across paired teams.

agent-loop — Skill for Claude Code by vinnie357

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 vinnie357/claude-skills --skill agent-loop

Clone the repo

git clone --depth 1 https://github.com/vinnie357/claude-skills

Made for: Claude Code.

Or install core, the plugin that ships this one along with the rest of its 14 skills, 5 commands, 7 agents, 1 hook.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vinnie357/claude-skills/agent-loop.svg)](https://agentmods.dev/skills/vinnie357/claude-skills/agent-loop)

Your own site

<a href="https://agentmods.dev/skills/vinnie357/claude-skills/agent-loop"><img src="https://agentmods.dev/badge/skills/vinnie357/claude-skills/agent-loop.svg" alt="Measured on agentmods" height="20"></a>

Per session 156 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 7,727 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: 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 Excessive Agency · line 298
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00156	$0.07727
Opus 5	$0.00078	$0.03864
Sonnet 5	$0.00031	$0.01545
Haiku 4.5	$0.00016	$0.00773

Measured yesterday against content hash 5deb9112a962, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agent-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 yesterday.

The scan reads SKILL.md. This mod also ships 2 executable files (templates/five-tier-issue.workflow.js, templates/forge-issue.workflow.js), 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.

plugins/core/skills/agent-loop/SKILL.md · 399 lines

How it starts

The opening of the file, as written. The whole thing — 399 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Loop

Defines the standard workflow for agents working epics, issues, and tasks through a 4-phase execution model with a 6-tier prompt hierarchy.

Forge — the default operating model

Forge is the name for how this skill works an issue: paired teams of strong-model principals and cheap read-only hands, fanned out across the issue's slices, with reviewers on the best-thinker model. Forge is the implied default for all work — the lead applies it without being told to "use the 5/6-tier system."

Activate Forge by work phrasing ("work epic/issue ", acting on bees ready), by forge <id> in a mission / spawn prompt, or by the /work command in an interactive session — all load this skill and run Forge on the target.

Two disciplines make Forge cheap and reliable:

Hands do the searching. Principals (planners, reviewers) never run their own Grep/Glob/large-Read sweeps. They spawn focused read-only hands on the smallest fast model, receive a file:line index, and Read only those lines. See references/researcher.md.
Paired teams fan out. Every issue runs the same paired structure; fan-out width N = the planner's slice count (N=1 for a small issue, same path). See references/forge.md.

Required plugins

Assumes both core@vinnie357 (this plugin) and claude-code@vinnie357 (agent/team file formats, referenced by name in spawning steps) are installed. Standalone core still describes the workflow, but cross-plugin skill names like /claude-code:claude-agents won't resolve until claude-code@vinnie357 is installed too — treat those references as procedural-only until then.

4-Phase Execution

Every agent, regardless of tier, follows these four phases:

Phase	Name	Purpose
1	Pre-flight	Load skills, check tracker, verify branch, understand assignment
2	Working	Execute work items. Before any spawn: re-verify core skills loaded, load `/claude-code:claude-agents` always, load `/claude-code:claude-teams` for ≥2 parallel workers.
3	Validation	Run strictest CI suite, iterate with fix agent until clean
4	Submit	Create PR, wait for CI, report to upstream, clean up after merge

Read the full file on GitHub · 399 lines

Files

What ships with it

17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

yesterday Changed 5deb9112a962
4d ago Changed · +8 lines 791122dccd6b
4d ago Changed · +9 lines e7cc1021e431
8d ago First seen · 382 lines · 156 tokens per session scan A 6a43955dc408

Subscribe to this mod's changes

agent-loop is a skill published in the GitHub repository vinnie357/claude-skills (25 stars, last pushed 2d ago), licensed MIT. It adds 156 tokens to every session and 7,727 once invoked, about $0.0008 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 2026-08-30.

Building agents Project management

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

story-readiness

Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…

Donchitos/Claude-Code-Game-Studios · 77 tokens

autotask-creator

Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.

Orkas-AI/Orkas · 5 tokens

monorepo-management

Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.

wshobson/agents · 54 tokens