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/zhpeng24/devkit/production-statisticsnpx skills add zhpeng24/devkit --skill production-statisticsgit clone --depth 1 https://github.com/zhpeng24/devkitWhat 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 | $0.00056 | $0.00989 |
| Opus 5 | $0.00028 | $0.00495 |
| Sonnet 5 | $0.00011 | $0.00198 |
| Haiku 4.5 | $0.00006 | $0.00099 |
Grade A, and why
production-statistics 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 2d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Production Statistics
Answer production metric questions with bounded, read-only aggregate queries and sanitized outputs. Keep this workflow separate from deployment and debugging.
Trigger gate
Use only when all are true:
- the user explicitly identifies production/live data or an approved production reporting source;
- the request defines or implies a metric, time range, or reporting question;
- the result can be produced without changing data or schema.
Do not trigger merely because a development task mentions users, requests, counts, or a dashboard. Clarify the environment, metric definition, time window, timezone, filters, and dimensions only when they materially change the result.
Resolve the data contract
- Read
.devkit/project.jsonand repository reporting docs when present. - Resolve the approved production target, database engine, connection mechanism, timezone, read-only role, query limits, and approved relations or sanitized views. Never guess credentials, hosts, container names, or schemas.
- Use a dedicated statistics role. Do not reuse an application owner, administrator, superuser, deployment account, or shared developer credential.
- If the read-only role or approved access path does not exist, stop and request a
separate authorized DBA/deployment task. See
references/read-only-database.md.
Project configuration supplies defaults, not authorization. Keep credentials in the approved secret channel and out of prompts, commands, repository files, screenshots, charts, and reports.
Read-only contract
Allowed:
SELECT, read-only CTEs,SHOW, and metadata reads;- aggregate counts, sums, rates, percentiles, distributions, and bounded trends;
- session-local timeouts and explicit read-only transactions.
Forbidden:
- DML, DDL, procedure calls, grants, role changes, locks,
SELECT ... FOR UPDATE, temporary objects, indexes, refreshes, maintenance commands, or exports of raw sensitive records; - marking, cleaning, backfilling, repairing, or optimizing production data;
- querying with an administrator because the read-only account is inconvenient.
What ships with it
2 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.
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.
- 2d ago First seen · 112 lines · 56 tokens per session scan A 2930d9a47e7e
production-statistics is a skill published in the GitHub repository zhpeng24/devkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 989 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.