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 skills add Jerrylalala/compound-engineering --skill ce-product-pulsegit clone --depth 1 https://github.com/Jerrylalala/compound-engineeringWrote 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/jerrylalala/compound-engineering/ce-product-pulse)<a href="https://agentmods.dev/skills/jerrylalala/compound-engineering/ce-product-pulse"><img src="https://agentmods.dev/badge/skills/jerrylalala/compound-engineering/ce-product-pulse/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/jerrylalala/compound-engineering/ce-product-pulse"><img src="https://agentmods.dev/badge/skills/jerrylalala/compound-engineering/ce-product-pulse.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 | $0.00032 | $0.03227 |
| Opus 5 | $0.00016 | $0.01614 |
| Sonnet 5 | $0.00006 | $0.00645 |
| Haiku 4.5 | $0.00003 | $0.00323 |
Grade A, and why
ce:product-pulse 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 9d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Pulse
ce-product-pulse queries the product's data sources for a given time window and produces a compact, single-page report covering usage, performance, errors, and followups. The report is saved to docs/pulse-reports/ and the key points are surfaced in chat.
The skill does not mutate the product, the database, or any external system. Its only writes are pulse settings appended to .compound-engineering/config.local.yaml (the unified CE local config, gitignored, machine-local) and the report file (docs/pulse-reports/...). MCP and other data-source tools are invoked read-only; if a tool offers write modes, do not use them.
Interaction Method
Default to the platform's blocking question tool: AskUserQuestion in Claude Code (call ToolSearch with select:AskUserQuestion first if its schema isn't loaded), request_user_input in Codex, ask_user in Gemini, ask_user in Pi (requires the pi-ask-user extension). Fall back to numbered options in chat only when no blocking tool exists in the harness or the call errors (e.g., Codex edit modes) — not because a schema load is required. Never silently skip the question.
Ask one question at a time. Reserve multi-select for first-run configuration only.
Lookback Window
#$ARGUMENTS
Interpret the argument as a time window. Common forms:
24h,48h,72h- trailing hours7d,30d- trailing days1h- short-window (useful during launches)
If the argument is empty, default to pulse_lookback_default from config (resolved in Phase 0); if that is also unset, fall through to the hard default of 24h. If the argument is unparseable, ask the user to clarify.
Apply a 15-minute trailing buffer to the window's upper bound. Many analytics and tracing tools have ingestion lag; querying right up to now under-reports the most recent events. For a 24h window, query [now - 24h - 15m, now - 15m].
Core Principles
- Read it like a founder. No hardcoded thresholds. Do not label things "bad" or "good" by default - present the numbers and let the reader judge.
- Single page. Target 30-40 lines of terminal output. If the report is getting long, cut.
- No PII in saved reports. Do not include user emails, account IDs, or message content in the report written to disk.
- Parallel where safe, serial where it matters. Analytics and tracing queries run in parallel. Database queries run serially to avoid load.
- Memory through saved reports. Every run writes to
docs/pulse-reports/so past pulses are browseable as a timeline. - Read-only database access only. If a database is used as a data source, the connection must be read-only. The interview refuses to accept read-write credentials. Database access is optional - many products complete the pulse with analytics and tracing alone.
- Strategy-seeded when available. If
STRATEGY.mdexists, the interview reads it before asking questions and carries forward the product name and key metrics as seeds. The goal of data-source setup is to wire up whatever connections are needed to actually measure those metrics.
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.
- 9d ago First seen · 181 lines · 32 tokens per session scan A b9aee7545a6c
ce:product-pulse is a skill published in the GitHub repository Jerrylalala/compound-engineering (5 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 3,227 once invoked, about $0.0002 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.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…