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/jcodesmore/fix-claude-code/fixclaudenpx skills add JCodesMore/fix-claude-code --skill fixclaudegit clone --depth 1 https://github.com/JCodesMore/fix-claude-codeWhat 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 | $0.00169 | $0.01781 |
| Opus 5 | $0.00084 | $0.00890 |
| Sonnet 5 | $0.00034 | $0.00356 |
| Haiku 4.5 | $0.00017 | $0.00178 |
Grade B, and why
fixclaude scanned grade B with 1 finding 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Read the user's current settings file at `~/.claude/settings.json`. Parse the existing `env` block and top-level fields. Note which of the core fixes are already applied vs missing. How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix Claude Code — Interactive Performance Wizard
Run an interactive wizard that detects the user's current Claude Code configuration, applies proven performance fixes, and optionally installs powerful companion tools. Walk through every step in plain language so any user — beginner or expert — understands what's happening and why.
Tone & Style
Keep explanations short, friendly, and jargon-free. One or two sentences per setting. Use simple analogies when helpful. Never assume the user knows what an environment variable is — just show what changes and why it helps.
Wizard Flow
Step 1: Welcome & Detect Current State
Display a brief welcome message explaining what the wizard does.
Read the user's current settings file at ~/.claude/settings.json. Parse the existing env block and top-level fields. Note which of the core fixes are already applied vs missing.
If the file doesn't exist, note that a fresh settings file will be created.
Step 2: Core Performance Fixes
Load references/core-settings.md for the detailed explanation of each setting.
Present all 8 core fixes in a clear table showing:
- Setting name
- What it does (plain English, one line)
- Current value → Recommended value
The 8 core fixes are:
| Setting | Purpose |
|---|---|
CLAUDE_CODE_EFFORT_LEVEL |
Max reasoning every turn |
CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING |
Consistent deep thinking |
MAX_THINKING_TOKENS |
Maximum reasoning budget |
CLAUDE_CODE_DISABLE_1M_CONTEXT |
More compute for thinking |
alwaysThinkingEnabled |
Extended thinking every turn |
CLAUDE_CODE_NO_FLICKER |
Smooth screen rendering |
CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC |
Disable telemetry and background network |
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS |
Multi-agent coordination |
Note: Mention that CLAUDE_CODE_EFFORT_LEVEL=max uses more tokens per turn (higher cost on API plans; included on Max subscriptions). Also note that agent teams (CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS) uses significantly more tokens when active (~7x) — it enables the capability but does not activate by default, so there is no cost unless the user explicitly uses agent teams.
What ships with it
4 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.
- 2d ago First seen · 130 lines · 169 tokens per session scan B 0719d6c16896
fixclaude is a skill published in the GitHub repository JCodesMore/fix-claude-code (20 stars, last pushed 18d ago), licensed MIT. It adds 169 tokens to every session and 1,781 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
geo-technical
Technical SEO audit with GEO-specific checks — crawlability, indexability, security, performance, SSR, and AI crawler access.
evalscope
LLM evaluation & inference performance testing via the evalscope CLI. Translates natural language requests into evalscope commands for: (1) Model accuracy evaluation — runs 160+ benchmarks against local checkpoints or API endpoints (OpenAI-compatible, Anthropic, LiteLLM); (2) Performance stress testing — TTFT, TPOT…
hotpath_init
Configure hotpath profiling in a Rust project. Adds the hotpath dependency with feature-gated setup, instruments main with hotpath::main, functions with measure/measureall, and wraps channels, mutexes, rwlocks, streams, futures, reqwest clients, axum routers and byte-level I/O with hotpath macros. Use when the user…
hotpath_bump
Bump the hotpath version number across the workspace and related files. Updates crate versions in Cargo.toml files (exact patch version) and version references in the backend middleware, hotpathinit skill, and README (major.minor only). Use when the user wants to bump, bump the version, or release a new hotpath…
opentelemetry-net-instrumentation
Provides guidance for implementing OpenTelemetry instrumentation in .NET codebases, covering tracing (Activities/Spans), metrics, logs, naming conventions, error handling, performance, SDK setup, resources, context propagation, and API design best practices.
database-performance
Database access patterns for performance. Separate read/write models, avoid N+1 queries, use AsNoTracking, apply row limits, and never do application-side joins. Works with EF Core and Dapper.