iterate-skill

iterate-skill is a skill for Claude Code from hyhmrright/logic-lens. It costs 183 tokens per session (1,766 once invoked), scanned A, original, MIT.

A repeatable improvement workflow for raising a coding skill’s evaluation score by finding failures, making small edits, testing again, and checking whether the result actually improved.

In plain words
What is it for?
Use it to improve a skill, diagnose failing evaluation modes, edit its instructions, rerun evaluations, and continue until the results are clean.
Why use it?
It replaces guesswork with a cycle that identifies specific problems and verifies that changes improve the skill without merely fitting a particular test.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Part of the logic-lens plugin — 11 skills, 6 commands, 3 agents, 2 hooks shipped together

Good fit Use it to improve a skill, diagnose failing evaluation modes, edit its instructions, rerun evaluations, and continue until the results are clean.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hyhmrright/logic-lens/iterate-skill
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 hyhmrright/logic-lens --skill iterate-skill
Clone the repo
git clone --depth 1 https://github.com/hyhmrright/logic-lens

Made for: Claude Code.

Or install logic-lens, the plugin that ships this one along with the rest of its 11 skills, 6 commands, 3 agents, 2 hooks.

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 iterate-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/hyhmrright/logic-lens/iterate-skill/github.svg)](https://agentmods.dev/skills/hyhmrright/logic-lens/iterate-skill)
Your own site
<a href="https://agentmods.dev/skills/hyhmrright/logic-lens/iterate-skill"><img src="https://agentmods.dev/badge/skills/hyhmrright/logic-lens/iterate-skill/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for iterate-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/hyhmrright/logic-lens/iterate-skill"><img src="https://agentmods.dev/badge/skills/hyhmrright/logic-lens/iterate-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 183 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,766 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 pass 7 Sept 2026
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00183 $0.01766
Opus 5 $0.00092 $0.00883
Sonnet 5 $0.00037 $0.00353
Haiku 4.5 $0.00018 $0.00177

Measured 10d ago against content hash 22cc9b50c1bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

iterate-skill 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 10d 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/iterate-skill/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

iterate-skill — the Logic-Lens improvement loop

This is the harness orchestrator. It coordinates three agents and two support skills into one deterministic loop that raises a skill's eval score without overfitting or grader-gaming.

Execution mode: sub-agent pipeline (generate → test → verify). Each step's output is the next step's input, handed off through the filesystem (skills-workspace/iteration-<TAG>/) and agent return values. There is no peer-to-peer team chatter, so agents are spawned via the Agent tool — always with model: "opus", and subagent_type set to the agent's own definition name (e.g. subagent_type: "skill-editor"), not "general-purpose" — passing general-purpose would discard the role/principles in .claude/agents/<name>.md, defeating the harness. Agents return results to this orchestrator, which owns state and the ship/rollback decisions.

Agents (who) — all in .claude/agents/, spawn by these exact subagent_type names:

subagent_type Role
eval-failure-analyzer Read-only: cluster failures, map to eval IDs, propose minimal edits
skill-editor Apply one minimal, generalized edit; refuse grader edits
iteration-guard Verify net gain vs variance; recommend SHIP / ROLLBACK / RERUN (orchestrator executes any revert)

Support skills (how): sync-skill-cache (mandatory pre-eval gate), run-iteration-eval (run + grade).

Phase 0 — context check (initial / resume / partial)

Determine the run mode before doing anything:

  • ls -dt skills-workspace/iteration-*/ — if recent iterations exist and the user asks to "continue" or "another pass" → resume: use the latest as baseline, skip re-baselining.
  • User provides a fresh target skill / new failure → initial: establish a baseline first (Phase 1).
  • User asks to redo just one mode or one skill → partial: scope the eval to the affected case IDs.

Confirm the target skill (which of the six logic-*) and the failing mode with the user if ambiguous — do not guess which skill to mutate.

Read the full file on GitHub · 118 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. 10d ago First seen · 118 lines · 0 tokens per session scan A 22cc9b50c1bb

Subscribe to this mod's changes

iterate-skill is a skill published in the GitHub repository hyhmrright/logic-lens (22 stars, last pushed 11d ago), licensed MIT. It adds 183 tokens to every session and 1,766 once invoked, about $0.0009 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

integration-e2e-testing

Integration and E2E test design principles, ROI calculation, test skeleton specification, and review criteria. Use when designing integration tests, E2E tests, or reviewing test quality.

shinpr/claude-code-workflows · 42 tokens

brooks-health

Combined codebase health dashboard that scores a project across all four quality dimensions — PR quality, architecture, tech debt, and test quality — in a single pass, drawing on twelve classic engineering books. Triggers when: user wants an overall quality assessment, asks "how healthy is this codebase?", "run all…

hyhmrright/brooks-lint · 156 tokens

brooks-sweep

Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…

hyhmrright/brooks-lint · 178 tokens

brooks-test

Test quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of Unit Testing, How Google Tests Software, and Working Effectively with Legacy Code — that diagnoses structural problems in an existing test suite: brittleness, mock abuse, coverage illusions, slow…

hyhmrright/brooks-lint · 161 tokens

recipe-add-integration-tests

Add integration/E2E tests to existing codebase using Design Docs.

shinpr/claude-code-workflows · 19 tokens

testing-principles

Language-agnostic testing principles including TDD, test quality, coverage standards, and test design patterns. Use when writing tests, designing test strategies, or reviewing test quality.

shinpr/claude-code-workflows · 40 tokens