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/centminmod/my-claude-code-setup/session-metricsnpx skills add centminmod/my-claude-code-setup --skill session-metricsgit clone --depth 1 https://github.com/centminmod/my-claude-code-setupWrote 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/centminmod/my-claude-code-setup/session-metrics)<a href="https://agentmods.dev/skills/centminmod/my-claude-code-setup/session-metrics"><img src="https://agentmods.dev/badge/skills/centminmod/my-claude-code-setup/session-metrics.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 | $0.00182 | $0.07827 |
| Opus 5 | $0.00091 | $0.03914 |
| Sonnet 5 | $0.00036 | $0.01565 |
| Haiku 4.5 | $0.00018 | $0.00783 |
Grade B, and why
session-metrics 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 4d 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
assistant text are truncated to ~240 characters with a **Show full prompt** / **Show full response** toggle that reveals the full text (up How it starts
The opening of the file, as written. The whole thing — 474 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Metrics
Runs scripts/session-metrics.py against the Claude Code JSONL log to produce
a timeline-ordered cost summary with per-turn and cumulative totals.
Dispatch — how to route this invocation
First positional argument received: $ARGUMENTS[0]
Full argument string: $ARGUMENTS
Read $ARGUMENTS[0] above and match it by literal equality against the
table below. Claude Code already tokenized the arguments shell-style, so no
parsing is required — just compare strings.
$ARGUMENTS[0] |
Route | Then read |
|---|---|---|
all-projects |
Instance-wide dashboard aggregating every project under ~/.claude/projects |
## Instance dashboard (all projects) below |
compare |
Two-session compare on JSONLs that already exist | ## Model comparison below, then references/model-compare.md before running |
compare-run |
Fully automated capture: spawns two claude -p sessions, feeds the suite, then runs --compare |
## Model comparison below, then references/model-compare.md "Workflow A — automated" |
compare-prep |
Print manual capture protocol + 10-prompt suite (fallback when headless is unavailable) | ## Model comparison below |
count-tokens |
API-key-only tokenizer check | ## Model comparison below |
export |
Natural-language export shortcut — scan full arg string to determine session vs project scope | ## Export shortcuts below |
project |
All sessions for the current project — timeline + per-session subtotals + grand total | ## Quick usage below (--project-cost); also scan remaining args for --output format flags |
project-cost |
Alias for project |
## Quick usage below (--project-cost); also scan remaining args for --output format flags |
| (empty, or any other value) | Default single-session report | ## Quick usage below |
What ships with it
54 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.
- CHANGELOG.md 181 KB
- references/custom-prompts.md 5.9 KB
- references/instance-dashboard.md 3.9 KB
- references/jsonl-schema.md 33 KB
- references/model-compare.md 32 KB
- references/model-compare/fixtures/compare-fixture-integration-tests.md 823 B
- references/model-compare/fixtures/compare-fixture-release-checks.md 868 B
- references/model-compare/fixtures/compare-fixture-unit-tests.md 831 B
- references/model-compare/prompts/01_claudemd_summarise.md 2.6 KB
- references/model-compare/prompts/02_english_prose.md 1.3 KB
- references/model-compare/prompts/03_code_review.md 1.9 KB
- references/model-compare/prompts/04_stack_trace_debug.md 1.7 KB
- references/model-compare/prompts/05_tool_heavy_task.md 1.0 KB
- references/model-compare/prompts/06_cjk_prose.md 1.5 KB
- references/model-compare/prompts/07_json_reshape.md 1.9 KB
- references/model-compare/prompts/08_csv_transform.md 1.4 KB
- references/model-compare/prompts/09_typescript_refactor.md 1.3 KB
- references/model-compare/prompts/10_instruction_stress.md 1013 B
- references/platform-notes.md 3.8 KB
- references/post-export-audit.md 2.2 KB
- references/pricing.md 18 KB
- references/tasks-companion.md 6.0 KB
- scripts/_analytics.py 24 KB runs code
- scripts/_charts.py 35 KB runs code
- scripts/_cli.py 65 KB runs code
- scripts/_constants.py 1.4 KB runs code
- scripts/_data.py 133 KB runs code
- scripts/_dispatch.py 94 KB runs code
- scripts/_dt.py 1.3 KB runs code
- scripts/_health.py 24 KB runs code
- scripts/_html_sections.py 319 KB runs code
- scripts/_invariants.py 6.9 KB runs code
- scripts/_json_export.py 8.4 KB runs code
- scripts/_md_render.py 76 KB runs code
- scripts/_report.py 77 KB runs code
- scripts/_time_of_day.py 4.8 KB runs code
- scripts/_turn_parser.py 52 KB runs code
- scripts/_tz.py 6.1 KB runs code
- scripts/_user_prompt.py 2.4 KB runs code
- scripts/session_metrics_compare.py 215 KB runs code
- scripts/session-metrics-quick.sh 5.9 KB runs code
- scripts/session-metrics.py 56 KB runs code
- scripts/vendor/charts/chartjs/v4/chart.umd.js 204 KB runs code
- scripts/vendor/charts/chartjs/v4/LICENSE.txt 1.1 KB
- scripts/vendor/charts/highcharts/v12/export-data.js 15 KB runs code
- scripts/vendor/charts/highcharts/v12/exporting.js 31 KB runs code
- scripts/vendor/charts/highcharts/v12/highcharts-3d.js 45 KB runs code
- scripts/vendor/charts/highcharts/v12/highcharts.js 269 KB runs code
- scripts/vendor/charts/highcharts/v12/LICENSE.txt 1.0 KB
- scripts/vendor/charts/manifest.json 2.1 KB
- scripts/vendor/charts/README.md 7.2 KB
- scripts/vendor/charts/uplot/v1/LICENSE.txt 1.1 KB
- scripts/vendor/charts/uplot/v1/uPlot.iife.min.js 50 KB runs code
- scripts/vendor/charts/uplot/v1/uPlot.min.css 1.8 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.
- 4d ago First seen · 474 lines · 182 tokens per session scan B 554b182dd0b8
session-metrics is a skill published in the GitHub repository centminmod/my-claude-code-setup (2,614 stars, last pushed 1mo ago), licensed MIT. It adds 182 tokens to every session and 7,827 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
memory-bank
Token-efficient persistent memory system for Claude Code that saves 67% tokens on session warm-up (verified with tiktoken). Layered architecture with progressive loading, compact encoding, branch-aware context, smart compression, session diffing, conflict detection, session continuation protocol, and recovery mode.…
building-chatgpt-apps
Guides creation of ChatGPT Apps with interactive widgets using OpenAI Apps SDK and MCP servers. Use when building ChatGPT custom apps with visual UI components, embedded widgets, or rich interactive experiences. Covers widget architecture, MCP server setup with FastMCP, response metadata, and Developer Mode…
memory-systems
Design and implement memory architectures for agent systems. Use when building agents that need to persist state across sessions, maintain entity consistency, or reason over structured knowledge.
multi-agent-patterns
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.
scaffolding-openai-agents
Builds AI agents using OpenAI Agents SDK with async/await patterns and multi-agent orchestration. Use when creating tutoring agents, building agent handoffs, implementing tool-calling agents, or orchestrating multiple specialists. Covers Agent class, Runner patterns, function tools, guardrails, and streaming…
tool-design
Design tools that agents can use effectively. Use when creating new tools for agents, debugging tool-related failures, or optimizing existing tool sets.