New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Loop Architect

by fabricioctelles in fabricioctelles/skills

Design well-structured agent loops with best-practice coaching and cross-model review gates before you run them.

MITAuto-check: notesAgent Workflows

Install Loop Architect

skills CLI
$ npx skills add fabricioctelles/skills --skill loop-architect -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install fabricioctelles/skills loop-architect --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/fabricioctelles/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/loop-architect .claude/skills/loop-architect && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
loop-architect
GitHub stars
106
Token cost
~2.1k tokens
SKILL.md length
692 words
Files
22 (incl. scripts, references)
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

Design well-structured agent loops with best-practice coaching and cross-model review gates before you run them.

  • Works in 11 steps: Resolve the target path from the user.… → Load the relevant rubric only when… → Interview in seven stages: goal,… → …
  • The user wants to design
  • SKILL.md covers Why This Exists, Workflow, Execution Paths and File Rules, plus 3 more sections
  • Runs Python scripts from its folder; calls python3

What it does

Loop Architect is an agent skill from fabricioctelles/skills. Design well-structured agent loops with best-practice coaching and cross-model review gates before you run them. Use when the user wants to design, build, or set up an agent loop, iterative agent workflow, self-review loop, LLM-as-judge loop, multi-model council, reviewer/judge gate, or goal-driven looping process. Guides goal refinement, typed verification criteria, reviewer/judge selection, privacy boundaries, termination guards, and observability, then emits a RUNINSESSION.md handoff prompt plus portable…

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 26 other files, including scripts and reference files (for example `examples/ai-workflow-mapping/LOOP.md`, `examples/ai-workflow-mapping/README.md` and `examples/ai-workflow-mapping/RUN_IN_SESSION.md`).

It sits in Agent Workflows, covering Autonomous loops, LLM evaluation and Human-in-the-loop approvals. The repository describes itself as: A collection of skills for AI agents (Kiro, Cursor, Windsurf, Claude Code, and others). Each skill is a reusable module that teaches the agent to perform complex tasks with… The licence is MIT.

When your agent uses it

  • The user wants to design
  • Set up an agent loop
  • Iterative agent workflow
  • Self-review loop

Example prompts

  • “/loop-architect”

Requirements

  • Python 3

Workflow steps

11 steps, taken from the first numbered list in SKILL.md.

  1. Resolve the target path from the user. Default: ./loop-architect-output. If
  2. Load the relevant rubric only when entering that stage
  3. Interview in seven stages: goal, verification, host model, council,
  4. Critique each stage before accepting it. Prefer concrete alternatives over
  5. Keep reviewer and judge roles distinct. A reviewer writes notes. A judge
  6. Require multiple termination guards: max_iterations, a revision cap on
  7. Before any cross-vendor council member is selected, state what context will
  8. Show an ASCII flow preview and ask for confirmation before final emission.
  9. Emit these files into the target
  10. After writing loop.yaml, compile it
  11. Ask whether the user wants to run the loop now. If yes

What it can do on your machine

Read from SKILL.md and the folder at commit f1de632. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Loop Architect loads about 2.1k tokens when it runs, and up to ~4.6k if it reads all its reference files. Until then it costs about 147 tokens; SKILL.md has 692 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~147
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:152
    - Default redaction globs: `.env`, `.env.*`, `secrets/**`, `**/*.key`.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from fabricioctelles/skills at commit f1de632, republished under its MIT licence (© fabricioctelles). 692 words, ~2,140 tokens.

Download SKILL.mdSave it as .claude/skills/loop-architect/SKILL.md (or your agent's skills folder). This skill also uses 21 other files; get the full folder from GitHub.
name
loop-architect
description
Design well-structured agent loops with best-practice coaching and cross-model review gates before you run them. Use when the user wants to design, build, or set up an agent loop, iterative agent workflow, self-review loop, LLM-as-judge loop, multi-model council, reviewer/judge gate, or goal-driven looping process. Guides goal refinement, typed verification criteria, reviewer/judge selection, privacy boundaries, termination guards, and observability, then emits a RUN_IN_SESSION.md handoff prompt plus portable loop.yaml, loop.resolved.json, LOOP.md, and run-loop.py.
metadata.author
https://ft.ia.br
metadata.version
1.1
metadata.date
2026-10-04
metadata.repository
https://github.com/fabricioctelles/skills
metadata.license
MIT
metadata.original_project
https://github.com/ksimback/looper
metadata.original_author
Kevin Simback (@ksimback)
metadata.attribution
Reinterpretation of Looper (MIT License) by Kevin Simback, adapted for Kiro CLI with native /goal, subagent, and review loop integration.
metadata.category
code-scaffolding-and-templates

Loop Architect

A loop design coach for Kiro CLI. Interviews you, critiques your design against built-in best-practice rubrics, wires in cross-model reviewers or judges, shows the loop as an ASCII flow preview, and writes portable artifacts you can run immediately with /goal or later with the Python runner.

Based on Looper by Kevin Simback, MIT License. Adapted for Kiro CLI by ft.ia.br.

Why This Exists

Kiro CLI ships /goal (autonomous loop with self-verification) and subagents (parallel pipelines with review loops). These execute a loop. Loop Architect helps you design one worth executing — with a coached goal, typed verification, a cross-model gate, and explicit termination guards.

/goalSubagent pipelineLoop Architect
Layerexecutionexecutiondesign (pre-flight)
Coaches your goalnonoyes
Typed verificationnonoyes (programmatic / judge / human)
Reviewer modelsame modelconfigurabledifferent model, by default
Portable artifactnonoloop.yaml + resolved spec
Runs the loopyesyesyes, via handoff

Workflow

  1. Resolve the target path from the user. Default: ./loop-architect-output. If the target contains an existing loop.yaml, treat as edit/resume.

  2. Load the relevant rubric only when entering that stage:

    • Goal stage: references/goal-rubric.md
    • Verification stage: references/verification-rubric.md
    • Council stage: references/council-rubric.md
    • Control stage: references/control-rubric.md
    • Model detection: references/model-detection.md

  3. Interview in seven stages: goal, verification, host model, council, gates/control, confirmation flow preview, emit/run option. In the control stage, cover execution boundary, isolation, no-progress signals, state, and run logging.

  4. Critique each stage before accepting it. Prefer concrete alternatives over vague warnings. Push weak goals toward outcome, scope, context, and done state. Push weak verification toward programmatic checks first, then judge rubrics, then human signoff.

  5. Keep reviewer and judge roles distinct. A reviewer writes notes. A judge returns a structured verdict. revise_until_clean must name a judge member or human as verdict_source.

  6. Require multiple termination guards: max_iterations, a revision cap on each gate, a no-progress stop, and either a budget cap or an explicit human stop point.

  7. Before any cross-vendor council member is selected, state what context will leave the user's machine, which CLI receives it, which redaction globs apply, and that both execution paths require first-send consent.

  8. Show an ASCII flow preview and ask for confirmation before final emission.

  9. Emit these files into the target:

    • loop.yaml
    • loop.resolved.json
    • LOOP.md
    • RUN_IN_SESSION.md
    • run-loop.py
    • loop-workspace/
    • README.md

  10. After writing loop.yaml, compile it:

    bash
    python3 ~/.kiro/skills/loop-architect/scripts/looper.py compile \
  <target>/loop.yaml \
  --out <target>/loop.resolved.json \
  --render <target>/LOOP.md \
  --session-prompt <target>/RUN_IN_SESSION.md

  11. Ask whether the user wants to run the loop now. If yes:

    • Easy path: Follow RUN_IN_SESSION.md directly, or suggest a /goal one-liner derived from the definition_of_done.
    • Subagent path: If the council uses a model with review_loop capability, offer to execute via a subagent pipeline with native review loops.
    • External path: Explain that run-loop.py is available for running later or outside the session.
Show full SKILL.md (235 more words)Show less

Execution Paths

Path 1: /goal (simplest)

When the loop is straightforward and the host is the current Kiro session:

/goal --max 12 <definition_of_done from loop.yaml>

This uses Kiro's native self-verification loop. No cross-model review, but fast and zero-config.

When a cross-model reviewer is needed and the host has subagent capability:

Implement the loop following RUN_IN_SESSION.md. Use a subagent as reviewer
with trigger "NEEDS_CHANGES" and max 3 iterations per gate.

This leverages Kiro's native loop_to mechanism for the plan and delivery gates.

Path 3: External Python runner (advanced)
bash
python3 ./loop-architect-output/run-loop.py

For scheduled runs, CI integration, or when you need strict budget enforcement.

File Rules

  • Write argv arrays, never shell command strings, for all model invocations.
  • Do not write API keys, tokens, or credentials into any emitted file.
  • Default redaction globs: .env, .env.*, secrets/**, **/*.key.
  • Keep loop.yaml human-readable and commented.
  • Keep RUN_IN_SESSION.md as the default/easy execution handoff.
  • Copy templates/run-loop.py exactly unless the user asks to edit it.

Helper Scripts

Detect model CLIs:

bash
python3 ~/.kiro/skills/loop-architect/scripts/looper.py detect-models --write

Register a custom CLI:

bash
python3 ~/.kiro/skills/loop-architect/scripts/looper.py register-model <id> \
  --invoke kiro-cli chat --trust-all-tools -p --authed

Compile and render:

bash
python3 ~/.kiro/skills/loop-architect/scripts/looper.py compile <target>/loop.yaml \
  --out <target>/loop.resolved.json \
  --render <target>/LOOP.md \
  --session-prompt <target>/RUN_IN_SESSION.md

Confirmation Flow Preview

text
+--------------------------------+
| 1. Goal + context              |
|    read sources                |
+--------------------------------+
              |
              v
+--------------------------------+
| 2. Draft plan.md               |
|    state -> state.json         |
+--------------------------------+
              |
              v
+--------------------------------+
| 3. Plan gate                   |
|    verdict: reviewer-1         |
+--------------------------------+
  | needs work -> revise <= 3 -> step 2
  | pass
              v
+--------------------------------+
| 4. Write delivery-N.md         |
|    log -> run-log.md           |
+--------------------------------+
              |
              v
+--------------------------------+
| 5. Delivery gate               |
|    verdict: reviewer-1         |
+--------------------------------+
  | needs work -> revise <= 3 -> step 4
  | pass
              v
+--------------------------------+
| 6. Final output                |
|    all gates clean             |
+--------------------------------+

Stops: pass gates | max 12 iterations | no progress x2 | budget 30m, $5.0

Emit Checklist

  • The goal has a clear outcome, scope boundary, context sources, and done state.
  • Verification criteria are typed as programmatic, judge, or human.
  • At least one criterion is not purely vibe-based.
  • Each revise_until_clean gate has a valid verdict_source.
  • Every external invocation is an argv array with a timeout.
  • Cross-vendor egress is scoped, redacted, and consent-gated.
  • loop_control has iteration, revision, no-progress, and budget caps.
  • Execution boundary and isolation are explicit.
  • Observability names a run-log.md and state.json path.
  • Compiled artifacts (loop.resolved.json, LOOP.md, RUN_IN_SESSION.md) pass validation before handoff.

© fabricioctelles, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 21 other files (scripts, references) in skills/loop-architect of fabricioctelles/skills.

  • SKILL.md
  • LICENSE
  • examples/ai-workflow-mapping/LOOP.md
  • examples/ai-workflow-mapping/README.md
  • examples/ai-workflow-mapping/RUN_IN_SESSION.md
  • examples/ai-workflow-mapping/inputs/process-notes.md
  • examples/ai-workflow-mapping/loop.resolved.json
  • examples/ai-workflow-mapping/loop.yaml
  • examples/ai-workflow-mapping/run-loop.py
  • examples/ai-workflow-mapping/scripts/check-loop-doc.py
  • references/control-rubric.md
  • references/council-rubric.md
  • references/goal-rubric.md
  • references/model-detection.md
  • references/verification-rubric.md
  • schemas
  • … and 6 more

Open the folder on GitHubat commit f1de632

Compare with similar skills

Loop Architect next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Loop Architect compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Loop Architect this skillfabricioctelles/skills106—~2.1kAutomated safety check: NotesMIT
Agents Best PracticesDenisSergeevitch/agents-best-practices2.4k—~7.4kAutomated safety check: PassMIT
Looperksimback/looper710—~2.7kAutomated safety check: NotesMIT
Autoresearchbyungjunjang/jangpm-meta-skills120—~6kAutomated safety check: WarnNone
Improving MCP ToolsPostHog/posthog40k—~1.5kAutomated safety check: PassCustom licence
Inngest AgentsAsymmetric-al/core381—~2.6kAutomated safety check: PassAGPL-3.0

Similar skills

  • Agents Best Practices

    DenisSergeevitch/agents-best-practices

    A skill your agent uses when designing, generating an MVP blueprint for, auditing, troubleshooting, refactoring, or explaining an agentic harness for any domain.

    2.4k GitHub stars~7.4k tokensUpdated 4 days ago
    AI & LLM EngineeringAuto-check passed

  • Looper

    ksimback/looper

    Scaffold a well-designed agent loop with best-practice coaching and a cross-model review council.

    710 GitHub stars~2.7k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check: notes

  • Autoresearch

    byungjunjang/jangpm-meta-skills

    Autonomously optimize a Claude Code skill or agent system by running it repeatedly, scoring outputs against evals, mutating owned artifacts (prompt, references, scripts, agent definitions), and…

    120 GitHub stars~6k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check: warnings

  • Improving MCP Tools

    PostHog/posthog

    Official

    Run an improve-my-MCP campaign: an autoresearch-style loop that measures the MCP agent experience with the eval harness, picks the highest-impact tool problem from production data, makes one bounded…

    40k GitHub stars~1.5k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Inngest Agents

    Asymmetric-al/core

    A skill your agent uses when building durable AI agents or agentic workflows with Inngest and AgentKit, including model calls, tool calls, multi-agent networks, human approval, realtime progress…

    381 GitHub stars~2.6k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Author Skill

    ericrisco/rsc-harness

    A skill your agent uses when authoring a NEW rsc skill or editing an existing one — scoping it to one job, writing the description that decides whether it ever loads, splitting the body into…

    174 GitHub stars~4.3k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from fabricioctelles/skills

All 15 skills in this repo

  • Motion Ad

    fabricioctelles/skills

    Produce a short motion-graphics video ad — a 15s Facebook/Instagram/TikTok spot — as a rendered MP4.

    106 GitHub stars~4.1k tokensUpdated 5 days ago
    Auto-check passed

  • Agent Plugin Eval

    fabricioctelles/skills

    Audit, score, and compare repositories containing portable Agent Plugins against the official Agent Plugins specification.

    106 GitHub stars~2.1k tokensUpdated 5 days ago
    Auto-check passed

  • Pier Cloud

    fabricioctelles/skills

    This skill should be used when the user needs to consume the Pier Cloud (Lighthouse) API for cloud cost management — including JWT authentication, listing contexts, workspaces, workspace groups, and…

    106 GitHub stars~1.1k tokensUpdated 5 days ago
    Auto-check: notes

  • Ralph Loop Kiro Specs

    fabricioctelles/skills

    Automated iterative agent runner for spec-based development in Kiro.

    106 GitHub stars~2.6k tokensUpdated 5 days ago
    Auto-check passed

  • Security Specialist

    fabricioctelles/skills

    Runs security audits on codebases — full scans, diff reviews, threat models, vulnerability triage, remediation guidance, and finding tracking.

    106 GitHub stars~2.8k tokensUpdated 5 days ago
    Auto-check passed

  • Skill Evaluation

    fabricioctelles/skills

    Evaluate any agent skill against a merged framework — Anthropic's Claude Code best practices plus Matt Pocock's writing-great-skills methodology — across 4 axes (Trigger, Structure, Steering…

    106 GitHub stars~3.8k tokensUpdated 5 days ago
    Auto-check passed

Categories

Questions about Loop Architect

What does Loop Architect do?

Design well-structured agent loops with best-practice coaching and cross-model review gates before you run them. Loop Architect is an agent skill from fabricioctelles/skills. Design well-structured agent loops with best-practice coaching and cross-model review gates before you run them.

When should I use Loop Architect?

Loop Architect fits situations like: the user wants to design; set up an agent loop; iterative agent workflow; self-review loop.

How do I install Loop Architect in Claude Code?

Run `npx skills add fabricioctelles/skills --skill loop-architect -a claude-code`. Or copy the skill folder (skills/loop-architect in fabricioctelles/skills) into .claude/skills/loop-architect in your project. Claude Code loads it when a task matches its description.

How do I install Loop Architect in Codex?

Run `npx skills add fabricioctelles/skills --skill loop-architect -a codex`. Or copy the skill folder (skills/loop-architect in fabricioctelles/skills) into .agents/skills/loop-architect in your project. Codex loads it when a task matches its description.

Can I use Loop Architect in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add fabricioctelles/skills --skill loop-architect -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/loop-architect, .gemini/skills/loop-architect, .github/skills/loop-architect and .opencode/skills/loop-architect in your project.

What does Loop Architect need to run?

Going by SKILL.md and its folder, Loop Architect needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Loop Architect access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Loop Architect safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Loop Architect use?

Loop Architect is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Loop Architect use?

About 2.1k tokens (SKILL.md is roughly 8.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.5k tokens, read only when the agent opens those files.

What are the alternatives to Loop Architect?

Skills that share tags, products or a category with Loop Architect: Agents Best Practices (DenisSergeevitch/agents-best-practices, 2.4k stars), Looper (ksimback/looper, 710 stars), Autoresearch (byungjunjang/jangpm-meta-skills, 120 stars) and Improving MCP Tools (PostHog/posthog, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Loop Architect?

fabricioctelles (a GitHub user) maintains it in fabricioctelles/skills, which has 106 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 4, 2026.

Source: fabricioctelles/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.