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/claude-plugins/session-metricsnpx skills add centminmod/claude-plugins --skill session-metricsgit clone --depth 1 https://github.com/centminmod/claude-pluginsWrote 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/claude-plugins/session-metrics)<a href="https://agentmods.dev/skills/centminmod/claude-plugins/session-metrics"><img src="https://agentmods.dev/badge/skills/centminmod/claude-plugins/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 3d 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 The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 186 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 1.7 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 53 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.
- 3d ago First seen · 474 lines · 182 tokens per session scan B 554b182dd0b8
session-metrics is a skill published in the GitHub repository centminmod/claude-plugins (10 stars, last pushed yesterday), with no licence file. 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 2026-08-31.
Other skills, from other repositories
git-workflow
Use when running claudikins-kernel:execute, decomposing plans into tasks, setting up two-stage review, deciding batch sizes, or handling stuck agents — enforces isolation, verification, and human checkpoints; prevents runaway parallelization and context death.
shipping-methodology
Use when running claudikins-kernel:ship, preparing PRs, writing changelogs, deciding merge strategy, or handling CI failures — enforces GRFP-style iterative approval, code integrity validation, and human-gated merges.
strict-enforcement
Use when running claudikins-kernel:verify, checking implementation quality, deciding pass/fail verdicts, or enforcing cross-command gates — requires actual evidence of code working, not just passing tests.
brain-jam-plan
Use when running claudikins-kernel:outline, brainstorming implementation approaches, gathering requirements iteratively, structuring complex technical plans, or facing analysis paralysis with too many options — provides iterative human-in-the-loop planning with explicit checkpoints and trade-off presentation.
thinking-log
Automatically creates and maintains a THINKINGLOG.md file that documents Claude's reasoning process, decisions, and problem-solving approach during implementation tasks. Use this skill when: (1) User requests documentation of thinking/reasoning process, (2) Working on complex multi-step implementations, (3) User wants…
workflow
Professional AI programming assistant with structured workflow (Research -> Ideate -> Plan -> Execute -> Optimize -> Review) for developers.