Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add bdfinst/agentic-dev-team/plugin install dev-teamWrote 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/bdfinst/agentic-dev-team/performance-metrics)<a href="https://agentmods.dev/skills/bdfinst/agentic-dev-team/performance-metrics"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/performance-metrics/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/bdfinst/agentic-dev-team/performance-metrics"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/performance-metrics.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 | $0.00052 | $0.03364 |
| Opus 5.5 | $0.00021 | $0.01346 |
| Sonnet 5.5 | $0.00010 | $0.00673 |
| Haiku 4.5 | $0.00005 | $0.00336 |
Grade A, and why
performance-metrics 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.
How it starts
The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Metrics
Overview
Schema and procedures for capturing performance data in .claude/metrics/. Metrics enable evidence-based evaluation of agent effectiveness, cost efficiency, and quality outcomes.
Constraints
- Never log credentials, API keys, or PII in metric entries
- Log entries are append-only; do not modify or delete existing JSONL records
- Log at task completion, not mid-task; mid-task state belongs in
.claude/memory/progress files - Use the defined JSONL schema; do not invent new top-level fields without updating the reference
Metric Categories
Targets discipline. Per CLAUDE.md → "Claims discipline", a numeric target may only ship if an instrument measures it. The instrumented metrics below cite their sensor; the rest read "Aspirational — no sensor yet" until one exists (tracked by #102 cost metering and #106 telemetry). Do not reintroduce bare numeric targets —
tests/docs/prose_honesty_test.batsenforces this across all shipped prose.
Efficiency Metrics
| Metric | Description | Target |
|---|---|---|
| Task completion time | Wall-clock time from request to delivery | Track trend, no fixed target |
| Token usage per task | Total input + output tokens consumed | Minimize for comparable quality |
| Agent loading overhead | Tokens spent on agent/skill file reads | Aspirational — no sensor yet |
| Context summarization frequency | How often summarization triggers per task | Aspirational — no sensor yet |
Quality Metrics
| Metric | Description | Target |
|---|---|---|
| First-pass acceptance rate | Tasks accepted without rework | Aspirational — no sensor yet |
| Rework count | Number of revision cycles per task | Aspirational — no sensor yet |
| Hallucination incidents | Outputs containing fabricated information | Aspirational — no sensor yet |
| Accuracy score | Correctness of structured data extraction | Aspirational — no sensor yet |
| Test coverage | Percentage of code covered by generated tests | Track per project |
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 · 266 lines · 52 tokens per session scan A d34441d81856
performance-metrics is a skill published in the GitHub repository bdfinst/agentic-dev-team (295 stars, last pushed 4d ago), licensed MIT. It adds 52 tokens to every session and 3,364 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.