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 opencue/cuecards --skill trace-mcp-refactoringgit clone --depth 1 https://github.com/opencue/cuecardsWrote 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/opencue/cuecards/trace-mcp-refactoring)<a href="https://agentmods.dev/skills/opencue/cuecards/trace-mcp-refactoring"><img src="https://agentmods.dev/badge/skills/opencue/cuecards/trace-mcp-refactoring/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/opencue/cuecards/trace-mcp-refactoring"><img src="https://agentmods.dev/badge/skills/opencue/cuecards/trace-mcp-refactoring.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 | $0.00039 | $0.00652 |
| Opus 5.5 | $0.00016 | $0.00261 |
| Sonnet 5.5 | $0.00008 | $0.00130 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
trace-mcp-refactoring 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.
This is a copy
100% identical to trace-mcp-refactoring — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
trace-mcp — Refactoring Workflow
Use this skill whenever you are about to rename, restructure, extract, or otherwise refactor code in a project indexed by trace-mcp. The goal is to never break cross-file references and never guess at what is affected.
When to Use
- Renaming a class, function, method, variable, or file
- Extracting a function or method
- Restructuring a module or splitting a file
- Changing a function signature
- Any change that touches more than one call site
Refactoring Workflow
1. Assess before touching anything
assess_change_risk({ file_path: "src/foo.ts" })
# or
assess_change_risk({ symbol_id: "<id>" })
This returns the risk level of the target change based on churn, complexity, fan-in/fan-out, and test coverage. Use it to decide whether to proceed, add tests first, or split the change.
2. Find what actually needs refactoring
get_refactor_candidates()
Do not guess. This surfaces high-complexity, high-churn, and anti-pattern-laden symbols that are the real refactor targets.
3. Know what will break
get_change_impact({ symbol_id: "<id>" })
Returns the reverse-dependency graph: every file, symbol, and test that depends on the target. Review this list before editing.
4. Quantify complexity
get_complexity_report({ file_path: "src/foo.ts" })
Gives you a baseline so you can verify the refactor actually reduced complexity.
Renaming a Symbol — MANDATORY Flow
Never rename with Edit and replace_all. It silently misses import sites, re-exports, type references, and cross-file usages.
# 1. Collision detection first
check_rename({ symbol_id: "<id>", target_name: "newName" })
# 2. Apply rename across ALL files (definition + every reference)
apply_rename({ symbol_id: "<id>", new_name: "newName" })
apply_rename updates the definition, imports, re-exports, call sites, JSX usages, and tests in one atomic operation.
Extracting a Function
extract_function({
file_path: "src/foo.ts",
start_line: 42,
end_line: 67,
new_name: "computeTotals"
})
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 · 87 lines · 39 tokens per session scan A 8cb8a409b09b
trace-mcp-refactoring is a skill published in the GitHub repository opencue/cuecards (6 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 652 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to trace-mcp-refactoring, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
autofix
Review and repair current local changes until they converge, or run Qwen Code Autofix issue and review workflows from GitHub Actions.
atomic-debug
Hypothesis-driven debugging skill. Use when a bug, test failure, crash, or unexpected behavior is reported. Auto-trigger on error pastes or "broken/doesn't work/failing" language. Explicit invocation: /atomic-debug. Output: symptom statement → hypothesis table → cheapest test first → root cause. No symptom-patching.…
code-review
Review code changes for concrete defects.
atomic-review
Compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", or invokes /atomic-review. Auto-triggers when reviewing pull requests.
sipcode-regress
Check the user's own local Claude Code and Codex logs for regressions after an update (prompt-cache misses, 5-minute cache TTL, uncached context, hourly cache rebuilds, Codex usage limit draining faster per token) and pin each one to the version that introduced it, using the Sipcode CLI. Use when the user asks whether…
assess-findings
Triage static analysis findings, grade them against recorded decisions, and accept noise or irrelevant items.