target-loop

A repeat-and-review method for improving an output such as code, writing, design, or a document. It defines what finished means, checks the starting quality, and records each improvement round.

In plain words
What is it for?
Use it when polishing an artifact, setting a quality bar, tracking iterations, and deciding when the result is ready.
Why use it?
It prevents stopping too early and keeps revisions focused on specific remaining problems.

Skill for Claude CodeCodex

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/floomhq/moto/target-loop
Any agent
npx skills add floomhq/moto --skill target-loop
Clone the repo
git clone --depth 1 https://github.com/floomhq/moto

Made for: Claude Code, Codex.

Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 634 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 $0.00074 $0.00634
Opus 5 $0.00037 $0.00317
Sonnet 5 $0.00015 $0.00127
Haiku 4.5 $0.00007 $0.00063

Measured 3d ago against content hash d7157fef91cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

target-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 3d 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.

claude/skills/target-loop/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Target Loop Skill

Purpose

A structured iterative improvement loop that continues until a target artifact reaches a defined quality bar. Prevents premature stopping and systematic drift from the goal.

Step 1: Define the target

Before iterating, clearly define:

  1. What is the artifact? (code, copy, design, document)
  2. What is "done"? (specific quality criteria, not subjective)
  3. What is the completion signal? (user says "good", tests pass, score threshold, etc.)
  4. Maximum iterations? (default: 10)

Example completion criteria:

  • "Copy: no filler words, every sentence earns its place, reads in under 60 seconds"
  • "Code: all tests pass, no TypeScript errors, no console.logs"
  • "Design: passes QA checklist, no overlapping elements, all text fits"

Step 2: Baseline assessment

Before iterating, assess the current state:

  • What's working well? (preserve this)
  • What's the biggest problem? (fix this first)
  • Score: X/10 with specific reasoning

Step 3: Iterate

For each iteration:

ITERATION N/[MAX]
Current score: X/10
Biggest issue: [specific problem]
Fix applied: [what was changed]
New score: X/10
Remaining issues: [list]

Iteration priorities:

  1. Fix the thing that matters most first
  2. Don't fix multiple independent problems at once (hard to verify)
  3. After each fix, re-evaluate the full artifact - one fix often creates another problem

Step 4: Completion check

Before stopping, verify:

  • Does the artifact meet ALL stated completion criteria?
  • Is there anything that would make a skeptical reviewer reject this?
  • Has the core goal been preserved through iterations?

If any check fails, continue iterating.

Step 5: Final output

When done:

TARGET LOOP COMPLETE
Iterations: N
Final score: X/10
What changed: [summary of improvements]
Result: [the final artifact]

Anti-patterns

  • Stopping at 8/10: "Good enough" is not the goal. If the bar was set, hit it.
  • Fixing symptoms: If the same type of issue keeps appearing, there's a root cause to fix.
  • Losing the core: Iterations can drift from the original goal. Re-read the target criteria every 3 iterations.
  • Infinite loops: Set a max iteration count. If not converging, the criteria may need refinement.

Read the full file on GitHub · 80 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. 3d ago First seen · 80 lines · 74 tokens per session scan A d7157fef91cc

Subscribe to this mod's changes

target-loop is a skill published in the GitHub repository floomhq/moto (32 stars, last pushed 2mo ago), licensed MIT. It adds 74 tokens to every session and 634 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

rulesync

Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.

dyoshikawa/rulesync · 64 tokens

agent-workspace-linux

Use when a task needs an isolated hidden Linux desktop or workspace-owned browser: GUI app QA, web/browser/shopping automation, sandboxed app observation, or stale workspace cleanup. Routes agent-workspace-linux MCP tools on demand. Does NOT apply to host desktop/Chrome control, generic MCP setup, or pure code/file…

ilysenko/codex-desktop-linux · 70 tokens

ss-component

Generate a new UI component following the StyleSeed design conventions.

bitjaru/styleseed · 14 tokens

loongsuite-pilot-insight

基于 LoongSuite Pilot / AI Coding Agent 日志生成事件洞察、组织洞察、数据质量、研发效能和 AI Native 使用类 SLS 报表时使用;包含 AI Coding 事件表语义,以及团队报表可选的部门维表、deptuser 组织关系、指标口径和公共 CTE,通常与 sls-dashboard-builder 一起使用。.

alibaba/loongsuite-pilot · 91 tokens

map-review

Interactive 4-section code review using monitor, predictor, and evaluator agents plus the user and maintainer role reviewers on current changes. Use when reviewing a diff, PR, or staged work before merge. Do NOT use to plan or implement; use map-plan or map-efficient.

azalio/map-framework · 58 tokens

runjam-defaults

Default constraints for every RunJam session. Defines output path conventions, dependency checking rules, fallback strategies, and file management discipline. This skill is auto-injected into every session — do not remove. Current session working directory: /Users/guizhan/work/code/runjam.

peintune/runjam · 59 tokens