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.
npx skills add catlog22/Claude-Code-Workflow --skill skill-iter-tunegit clone --depth 1 https://github.com/catlog22/Claude-Code-WorkflowWrote 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.
[](https://agentmods.dev/skills/catlog22/claude-code-workflow/skill-iter-tune)<a href="https://agentmods.dev/skills/catlog22/claude-code-workflow/skill-iter-tune"><img src="https://agentmods.dev/badge/skills/catlog22/claude-code-workflow/skill-iter-tune/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.
<a href="https://agentmods.dev/skills/catlog22/claude-code-workflow/skill-iter-tune"><img src="https://agentmods.dev/badge/skills/catlog22/claude-code-workflow/skill-iter-tune.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00067 | $0.03557 |
| Opus 5.5 | $0.00027 | $0.01423 |
| Sonnet 5.5 | $0.00013 | $0.00711 |
| Haiku 4.5 | $0.00007 | $0.00356 |
Grade A, and why
skill-iter-tune 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Iter Tune
Iterative skill refinement through execute-evaluate-improve feedback loops. Each iteration runs the skill via Claude, evaluates output via Gemini, and applies improvements via Agent.
Architecture Overview
┌──────────────────────────────────────────────────────────────────────────┐
│ Skill Iter Tune Orchestrator (SKILL.md) │
│ → Parse input → Setup workspace → Iteration Loop → Final Report │
└────────────────────────────┬─────────────────────────────────────────────┘
│
┌───────────────────┼───────────────────────────────────┐
↓ ↓ ↓
┌──────────┐ ┌─────────────────────────────┐ ┌──────────┐
│ Phase 1 │ │ Iteration Loop (2→3→4) │ │ Phase 5 │
│ Setup │ │ ┌─────┐ ┌─────┐ ┌─────┐ │ │ Report │
│ │─────→│ │ P2 │→ │ P3 │→ │ P4 │ │────→│ │
│ Backup + │ │ │Exec │ │Eval │ │Impr │ │ │ History │
│ Init │ │ └─────┘ └─────┘ └─────┘ │ │ Summary │
└──────────┘ │ ↑ │ │ └──────────┘
│ └───────────────┘ │
│ (if score < threshold │
│ AND iter < max) │
└─────────────────────────────┘
Chain Mode Extension
Chain Mode (execution_mode === "chain"):
Phase 2 runs per-skill in chain_order:
Skill A → ccw cli → artifacts/skill-A/
↓ (artifacts as input)
Skill B → ccw cli → artifacts/skill-B/
↓ (artifacts as input)
Skill C → ccw cli → artifacts/skill-C/
Phase 3 evaluates entire chain output + per-skill scores
Phase 4 improves weakest skill(s) in chain
Key Design Principles
- Iteration Loop: Phases 2-3-4 repeat until quality threshold, max iterations, or convergence
- Two-Tool Pipeline: Claude (write/execute) + Gemini (analyze/evaluate) = complementary perspectives
- Pure Orchestrator: SKILL.md coordinates only — execution detail lives in phase files
- Progressive Phase Loading: Phase docs read only when that phase executes
- Skill Versioning: Each iteration snapshots skill state before execution
- Convergence Detection: Stop early if score stalls (no improvement in 2 consecutive iterations)
What ships with it
8 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.
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.
- 1mo ago First seen · 383 lines · 67 tokens per session scan A e8e9f4c7d57c
skill-iter-tune is a skill published in the GitHub repository catlog22/Claude-Code-Workflow (2,124 stars, last pushed 4mo ago), licensed MIT. It adds 67 tokens to every session and 3,557 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
debugging-livekit-agents
Drives a multi-turn conversation with a LiveKit agent running locally to see what it does. Use when the user says "test my agent", "try my agent", "does this work", "why did it call that tool", "it says the wrong thing when I ask X", "test this change", or whenever you have edited an agent and need to check how it…
visual-acceptance
A visual final-review method for user-interface changes. It checks the rendered result with repeatable screenshots, pixel values, computed styles, and CSS layering checks across themes.
skillgrade-setup
Sets up and runs skillgrade evaluation pipelines for AI agents and Agent Skills. Use when initializing eval configurations, running trials, reviewing results, exporting reports, or integrating with CI. Don't use for writing grader scripts, general test authoring, or non-agentic documentation.
lov-atom-feature-dev
An end-to-end workflow for building a small, self-contained feature across its shared core, command-line tool, API, user interface, saved parameter presets, agent tool, and debugging panel. It uses one contract and shared test cases across the pieces.
lov-runtime-verification
Verify client runtime fixes on actual desktop builds, physical iOS/Android devices, React Native/Flutter hosts, and deployed Web/PWA browsers with comparable workloads and lifecycle checks.
lov-fix-until-no-error
A verification-focused debugging workflow that repeatedly runs specified checks, fixes the highest-priority failure, and stops when the checks pass or a genuine external blockage remains.