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 agentmods add skills/catlog22/claude-code-workflow/skill-tuningnpx skills add catlog22/Claude-Code-Workflow --skill skill-tuninggit 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-tuning)<a href="https://agentmods.dev/skills/catlog22/claude-code-workflow/skill-tuning"><img src="https://agentmods.dev/badge/skills/catlog22/claude-code-workflow/skill-tuning.svg" alt="Measured on agentmods" 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 | $0.00066 | $0.01633 |
| Opus 5 | $0.00033 | $0.00816 |
| Sonnet 5 | $0.00013 | $0.00327 |
| Haiku 4.5 | $0.00007 | $0.00163 |
Grade A, and why
skill-tuning 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 today.
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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Tuning
Autonomous diagnosis and optimization for skill execution issues.
Architecture
┌─────────────────────────────────────────────────────┐
│ Phase 0: Read Specs (mandatory) │
│ → problem-taxonomy.md, tuning-strategies.md │
└─────────────────────────────────────────────────────┘
↓
┌─────────────────────────────────────────────────────┐
│ Orchestrator (state-driven) │
│ Read state → Select action → Execute → Update → ✓ │
└─────────────────────────────────────────────────────┘
↓ ↓
┌──────────────────────┐ ┌──────────────────┐
│ Diagnosis Phase │ │ Gemini CLI │
│ • Context │ │ Deep analysis │
│ • Memory │ │ (on-demand) │
│ • DataFlow │ │ │
│ • Agent │ │ Complex issues │
│ • Docs │ │ Architecture │
│ • Token Usage │ │ Performance │
└──────────────────────┘ └──────────────────┘
↓
┌───────────────────┐
│ Fix & Verify │
│ Apply → Re-test │
└───────────────────┘
Core Issues Detected
| Priority | Problem | Root Cause | Fix Strategy |
|---|---|---|---|
| P0 | Authoring Violation | Intermediate files, state bloat, file relay | eliminate_intermediate, minimize_state |
| P1 | Data Flow Disruption | Scattered state, inconsistent formats | state_centralization, schema_enforcement |
| P2 | Agent Coordination | Fragile chains, no error handling | error_wrapping, result_validation |
| P3 | Context Explosion | Unbounded history, full content passing | sliding_window, path_reference |
| P4 | Long-tail Forgetting | Early constraint loss | constraint_injection, checkpoint_restore |
| P5 | Token Consumption | Verbose prompts, state bloat | prompt_compression, lazy_loading |
Problem Categories (Detailed Specs)
See specs/problem-taxonomy.md for:
- Detection patterns (regex/checks)
- Severity calculations
- Impact assessments
What ships with it
25 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.
- phases/actions/action-abort.md 4.1 KB
- phases/actions/action-analyze-requirements.md 11 KB
- phases/actions/action-apply-fix.md 5.6 KB
- phases/actions/action-complete.md 5.3 KB
- phases/actions/action-diagnose-agent.md 10 KB
- phases/actions/action-diagnose-context.md 7.4 KB
- phases/actions/action-diagnose-dataflow.md 9.9 KB
- phases/actions/action-diagnose-docs.md 8.4 KB
- phases/actions/action-diagnose-memory.md 9.1 KB
- phases/actions/action-diagnose-token-consumption.md 6.1 KB
- phases/actions/action-gemini-analysis.md 9.0 KB
- phases/actions/action-generate-report.md 7.0 KB
- phases/actions/action-init.md 4.5 KB
- phases/actions/action-propose-fixes.md 11 KB
- phases/actions/action-verify.md 6.7 KB
- phases/orchestrator.md 5.7 KB
- phases/state-schema.md 11 KB
- specs/category-mappings.json 11 KB
- specs/dimension-mapping.md 7.8 KB
- specs/problem-taxonomy.md 7.8 KB
- specs/quality-gates.md 6.7 KB
- specs/skill-authoring-principles.md 4.3 KB
- specs/tuning-strategies.md 11 KB
- templates/diagnosis-report.md 2.9 KB
- templates/fix-proposal.md 3.3 KB
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.
- today First seen · 168 lines · 66 tokens per session scan A 94ad5308da82
skill-tuning is a skill published in the GitHub repository catlog22/Claude-Code-Workflow (2,133 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 1,633 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
audit
Audit local Claude Code transcript usage and summarize likely token hotspots. Use when the user asks where Claude Code tokens are going or wants evidence before optimizing.
optimize
Diagnose and reduce Claude Code token usage for a project or session using context hygiene, model and effort routing, MCP minimization, output trimming/sanitizing, subagent discipline, and measurement. Use when the user asks to lower Claude Code token usage, cost, context bloat, or usage-limit burn.
setup
Interactive or guided project setup for Claude Code token optimizer settings. Use when the user asks to install, configure, setup, enable hooks, or choose token-saving options interactively.
spawn-agent
Spawn worker agents (Gemini CLI or Codex CLI) to keep main context clean. Use for implementation, codebase research, context gathering, or any scoped work that would pollute the orchestrator's context.
newsroom-style
Apply AP Style and common newsroom conventions when writing or editing news articles, briefs, and headlines. Use when drafting publishable copy, editing contributor submissions, or converting informal notes into news-ready language.
beat-brief
Draft a short daily beat briefing from a folder of incoming source documents. Use when the reporter wants a five-bullet summary of the day's material with attribution flags and follow-up actions.