NodeJSmith/cm-get-token-insights
skills-memory/cm-get-token-insights/SKILL.md
Use when the user asks about Claude token usage, wants to see how much they are spending on Claude, understand cache hit rates, review Claude Code workflow patterns, or get cost optimization recommendations.
$ install --global
skillsauthnpx skillsauth add NodeJSmith/Claudefiles cm-get-token-insightsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 27, 2026, 2:29 AM109.1s1 file scanned
SKILL.md
- name:
- cm-get-token-insights
- user-invocable:
- true
- description:
- >
Get Token Insights
Parse JSONL conversation files from ~/.claude/projects/*/ into per-turn analytics tables, then analyze both cost-optimization opportunities and Claude Code workflow patterns (skills, agents, hooks).
Step 1: Ingest
cm-ingest-token-data
First run processes all files (~100s for ~2500 files) — warn the user about the wait before running. Incremental runs complete in under 5s. The script populates analytics tables, deploys an interactive dashboard to ~/.claude-memory/dashboard.html (built from templates/dashboard.html), and prints a slim JSON blob to stdout (full data goes to dashboard only).
If the script exits non-zero, report the error and stop.
Step 1.5: Claude Code Feature Enrichment
After parsing the JSON stdout from Step 1, construct a personalized prompt for a claude-code-guide agent using the actual data — not generic descriptions. For each of the top 3 insights (by waste_usd), include verbatim: the finding text, root_cause text, waste_usd value, solution.action, and solution.detail. Also include the specific project names, counts, and numbers mentioned in the insight (e.g. "meta-ads-cli: 75 cliffs across 53 sessions") so the agent's response is grounded in the user's real usage patterns.
Spawn the agent with subagent_type: "claude-code-guide" in foreground (do not use run_in_background). Wait for the agent to return before proceeding to Step 2. Weave its suggestions into the analysis in Step 2.
Step 2: Analyze
Capture the JSON stdout from Step 1 as the analysis input. Analyze across four areas:
- Cost optimization — top insights by dollar waste: finding, root cause, concrete solution (show exact CLAUDE.md rule text if suggested), estimated savings. Include relevant Claude Code feature suggestions from Step 1.5. Add a top-line summary (total spend, session count, date range, avg cost/session) and model economics (cost by model, savings from switching routine tasks to cheaper models).
- Workflow patterns — skill usage and error rates, agent delegation patterns (subagent types, model overrides, unnecessary general-purpose usage), hook performance (slowest by total runtime, high error rates).
- Week-on-week trends — if the
trendsobject is non-empty, compare current vs prior window: improved/regressed metrics with likely causes, new/retired skills and hooks, hook latency deltas. Skip iftrendsis empty. - Project cost ranking — top 3 projects by spend; for the most expensive, identify what drives the cost.
Structure the analysis naturally based on what the data shows — don't force empty sections. Ask the user if they want to dive deeper into any specific project, skill, or insight.
Step 3: Open Dashboard
python3 -c "import webbrowser, pathlib; webbrowser.open((pathlib.Path.home() / '.claude-memory' / 'dashboard.html').as_uri())"
Note the dashboard is available for deeper exploration — Section 6 (Claude Code Ecosystem) has the new skill, agent, and hook charts.
Related Skills
NodeJSmith/mine.create-issue
development
VerifiedTrustedCommunity
Use when the user says: 'create an issue', 'file an issue', 'open an issue', 'write an issue', 'new issue for this'. Codebase-aware issue creation — investigates the code to produce well-structured issues with acceptance criteria, affected areas, and enough detail for automated triage.
1SKILL.mdUpdated May 28, 2026
NodeJSmith/mine.issues-triage
development
VerifiedTrustedCommunity
Use when the user says: 'triage issues', 'classify issues by complexity', 'assess issue complexity', 'find quick wins', 'which issues are small', 'batch issue assessment'. Batch codebase-aware issue triage — parallel Haiku subagents assess actual complexity and effort by reading the code, not just titles.
1SKILL.mdUpdated May 27, 2026
NodeJSmith/mine.review
development
VerifiedTrustedCommunity
Use when the user says: "review my changes", "run the reviewers", "code and integration review", "readability review", "maintainability review", "sniff test this", "WTF check", "code smells", "is this code any good", "fresh eyes on this branch", "review this directory", "check this module". Dispatches three parallel reviewers — code, integration, and a readability pass — and consolidates findings into one prioritized report.
1SKILL.mdUpdated May 26, 2026
NodeJSmith/mine.clean-code
development
VerifiedTrustedCommunity
Use when the user says: "clean code check", "style review", "LLM smell check", "code hygiene", "nitpick this", "style check", "find style sins", "nitpicker review", "anal retentive review", "exhaustive style review", "no-filter style report". Dispatches three parallel stylistic checkers — llm-checker (training-bias patterns), lazy-checker (deferred debt), and nitpicker (style hygiene) — and consolidates findings into a report organized by checker with a Summary section for orchestration consumption.
1SKILL.mdUpdated May 26, 2026