EveryInc

把 AI 编码代理的一次性会话变成能积累经验的循环工作流，让下一次改动比上一次省力。 EveryInc/compound-engineering-plugin 36 个 skill 组成的插件，围绕 brainstorm、plan、work、simplify、review、compound 六步循环搭工作流。可装进 14 种代理宿主，包括 Claude Code、Cursor、Codex、Kimi Code CLI、Cline、Grok Build、Devin、GitHub Copilot、Factory Droid、Qwen Code、OpenCode、Pi、oh-my-pi 和 Antigravity CLI。

Compound Engineering: AI skills that make each unit of engineering work easier than the last (26k stars) What it does All text below is quoted directly from the project README. >Official Compound Engineering plugin for Claude Code, Codex, Cursor, and more Philosophy: - Plan thoroughly before writing code with /ce-brainstorm and /ce-plan using one plan artifact that grows from requirements into implementation planning - Review to catch issues and calibrate judgment with /ce-code-review and /ce-doc-review - Codify knowledge so it is reusable with /ce-compound - Keep quality high so future changes are easy >/plugin marketplace add EveryInc/compound-engineering-plugin Repository EveryInc/compound-engineering-plugin Repository stats |Metric|Value| |:-|:-| |Stars|25,784| |Forks|2.0k| |Last release|compound-engineering-v3.33.2 (2026-10-29)| |Languages|TypeScript 64.4%, Python 24.1%, Shell 5.8%| |Contributors|116| |AI contributor accounts (Claude / Codex / Cursor / Copilot)|@claude (369 commits), @cursoragent (28 commits)| |AI co-authored commits|Claude: 374, Cursor: 28| Main contributor |Field|Value| |:-|:-| |Name|Trevin Chow| |GitHub|@tmchow| |Commits to this repo|916 (top contributor)| |Bio|Exploring and building. Ex: Big Cartel, Nike, Sketchy, Axon, Microsoft| |Company / Location|Seattle, WA| |Followers|700| ────────────────────────────── 📌 If you want to browse more repos like this, we've organized them by category and rankings here: bestgithubrepositories.com 🗂️ We're also archiving repos where possible, so useful projects don't disappear when they're removed from GitHub.

好家伙，就算审查少报 10 条，也可能是规则过滤了 10 条。 开源审查技能 ce-code-review 的新提交会统计移除、降级的发现。报告里得有过滤数。 只报剩余问题，汇报时连错题本都给收走了。 #代码评审 github.com/EveryInc/compound-engineering-plugin/b…

让一条 PR 同时改代码和审查规则，像让考生顺手改评分表。 开源插件 compound-engineering-plugin 今天的提交从目标分支读 审查规则文件。你要放宽鉴权检查？ 规则得先单独合并。 #AI代码审查 github.com/EveryInc/compound-engineering-plugin/c…

I built Ponder: a Claude Code skill for AI that knows when to speak — and when to shut up Right now, AI basically means pattern matching—and as soon as a model doesn't have a piece of information, or finishes finding the real bugs on Pass 1, it decides to make up or assume information just to fill the turn. Why? Because LLMs are trained to never stay silent. I built Ponder (bin/ponder + SKILL.md) by myself around a simple premise: AI that knows when to speak, and knows when to shut up. Sometimes a voice or a pass has nothing new to add, and silence should be a valid, mathematically verified output. And when it does speak, it should be able to act as someone else and view your software from another perspective—including the actual human emotions associated with using it. How it works 1. 4 Perspectives = 4 Delta Operations Instead of open-ended roleplay where agents talk over each other, Ponder runs 4 voices where each one owns only one mutation on an append-only JSONL ledger (findings.jsonl): - Dreamer (add): Enumerates every reviewable unit and discovers missing coverage. - Skeptic (delete): Falsifies and retracts claims that don't have concrete file:line proof. - Builder (edit): Grounds surviving findings in exact paths and verification steps. - Empath (change): Steps into the user's shoes—with the emotions associated with that state—and re-scores severity (must / should / could). 2. Silence is First-Class (voices vs. deltaVoices) Ponder separates who showed up to verify (voices) from who mutated the ledger (deltaVoices). A voice can inspect the entire ledger, agree nothing needs to change, and stay silent (0 deltas). When all 4 voices review 100% of the enumerated surface and emit 0 deltas across consecutive passes, the CLI outputs stop (converged). 3. Coverage Gate & 3-Way Ledger Verification Pass 1 is blocked from stopping until coverage == 1.00 of enumerated units are graded. Every finding is verified against disk and git history (Phantom Rule), and ponder verify reconciles session.json, passes/, and findings.jsonl. --- One-Shot Without Ponder vs. One-Shot With Ponder (K=5 Study + 3 Live Audits) Technically, typing "ponder this codebase" is still a single user prompt—the human sends one prompt while Ponder runs the multi-pass loop in the background. To factor out LLM temperature variance, I ran a K=5 repeated-measures study across a 12-module codebase comparing a standard one-shot prompt against a one-shot prompt with Ponder: - Precision: 56.8% (Standard) → 100.0% (Ponder) (Mann-Whitney U = 0, p = 0.0079) - Critical (must) Bug Recall: 56.0% → 100.0% (+44% more real bugs caught on Pass 2 via Dreamer's coverage gate) - False Positives: 3.8 / run → 0.0 / run (~43 mins of ghost-bug debugging saved per audit) I also ran 4-pass architecture audits today across 3 major open-source AI repos (72.3k+ combined stars): - steipete/CodexBar (22.9k★): Skeptic retracted a Pass-1 credential-file false alarm after verifying its 0700 + O_EXCL + atomic rename defense, while Builder verified a real POSIX_SPAWN_SETPGROUP race where kill(-pgid) can kill CodexBar.app's own process group (Issue #4829 — rated 🦞 diamond lobster by the repo's automated triage bot — + Fix PR #4830). - EveryInc/compound-engineering-plugin (25.7k★): Skeptic retracted a false path-traversal alarm, while catching codex.ts/pi.ts clobbering user symlinks and unbounded .bak.<ts> spam (Issue #1916 + Fix PR #1919). - coleam00/Archon (23.8k★): Skeptic retracted a false open-redirect alarm, while isolating a static signCookie("authenticated") token with no expiry/rotation binding and a double decodeURIComponent URIError crash (Issue #5256 + Fix PR #5257). --- How this relates to Caveman If you've seen the Caveman skill: Caveman makes speech very brief (syntax compression), which saves output tokens when the model talks, whereas Ponder silences forced speech altogether when a voice or pass has nothing true to add (epistemic compression). They actually complement each other really well. Repo & Install (MIT, zero dependencies, Node 18+) GitHub: **Quinnod345/ponder** git clone https://github.com/Quinnod345/ponder.git ~/.claude/skills/ponder ln -sf ~/.claude/skills/ponder/bin/ponder /usr/local/bin/ponder

every-marketplace ⭐ 26k A workflow automation tool for developers using Claude Code, provided as a plugin marketplace. 🔗 EveryInc/every-marketplace #opensource t.co

Agentic Coding in Software Teams: From Individual Tool to Governed Software Delivery System Most organizations begin with the wrong question: which coding agent should we buy? The tool matters, but the evidence points elsewhere. DORA's 2025 research describes AI mainly as an amplifier that magnifies an organization's existing strengths and weaknesses. It also finds that the greatest returns come from a strategic focus on the underlying organizational system, not from the tools themselves. dora That finding changes the adoption problem. If agents amplify what a team already is, a team with unclear requirements, flaky tests, and weak review habits will produce unclear, flaky, weakly reviewed changes faster. A team with explicit conventions, reliable verification, and disciplined review gets more from the same tool. The adoption task is therefore to build an environment where agent work is scoped, observable, verified, and accountable. This article walks through that idea in five parts: the human role, the rollout, the repository, the controls, and the measurement. It draws on the twenty-five sources above. Part 1: People decide what, agents decide how Anthropic analyzed about 400,000 interactive Claude Code sessions from October 2025 to April 2026 and found a clear division of labor. People decide what to build, and the agent decides how to build it. That is a useful default. It also shows where mistakes are costly: a weak "what" cannot be repaired by a strong "how". anthropic Addy Osmani frames this as management. His orchestration guide treats delegation, task briefs, monitoring, verification, and integration as the practical work of running agents. Martin Fowler's analysis describes how human responsibility shifts. Engineers inspect fewer individual outputs and put more effort into the specifications, checks, and guidance around the agent. addyosmani IBM's description of agentic engineering is a good outline of the workflow. Work is broken into tasks, assigned, orchestrated, reviewed, and iterated, with human engineers validating correctness, security, performance, maintainability, and alignment with requirements. The same source says teams need training in system design, not only prompting. ibm Part 2: Roll out deliberately Anthropic's rollout playbook recommends starting with a pilot group of 20–50 developers already comfortable with AI-assisted tools. It then suggests building internal expertise, creating custom commands for organizational workflows, and documenting standards in context files. It also recommends a dedicated channel for sharing practices and problems. To scale, it recommends internal champions and a kick-off hackathon instead of a phased rollout that leaves teams waiting their turn. resources.anthropic My deck's 30/60/90-day plan is a more conservative proposal of my own, not a published benchmark. For a regulated or enterprise setting, choosing a smaller first team is a reasonable adaptation. The principle that holds across sources is to prove the workflow before widening access. The GitHub and Anthropic guides agree on what makes a good first task. It should be well scoped, with clear acceptance criteria and a way to verify the result. Anthropic also recommends separating research and planning from implementation, so the agent does not solve the wrong problem. For larger features, it suggests having Claude interview the engineer and write a spec first. docs.github Part 3: Make the repository legible Agents work from what they can read. OpenAI's harness-engineering account describes repository-based knowledge, a concise entry-point file, and architecture enforcement as central to working with Codex at scale. The practical lesson is to keep the knowledge an agent needs in the repository, versioned and reviewable, not in someone's chat history. github Instruction files help, with limits. HumanLayer argues that shared instructions should stay focused, with task-specific knowledge moved into separate, discoverable documents. One community collection suggests keeping a CLAUDE.md under 200 lines, though that is a heuristic from the community, not a standard. Anthropic's guidance says to run /init to generate a starter file and refine it over time. Cursor's rules documentation shows the same idea for team-wide and repository-scoped guidance. code.claude The most useful content in these files is the exact test, build, and lint commands, architecture constraints, and team conventions that a linter does not enforce. Cursor's guide adds that persistent context and canonical examples are most valuable when an agent keeps repeating the same mistake. Compound Engineering turns this into a loop. Each cycle of planning, building, and reviewing ends by capturing lessons for the next one. github Part 4: Enforce, don't just instruct This is the point where adoption programs most often fail. Birgitta Böckeler's framework separates proactive guidance from feedback checks, and deterministic controls from AI-based judgment. An instruction asks an agent to follow a rule. A required check makes violations fail. beri Security shows the gap clearly. Fowler's VibeSec article argues that prompt-level security instructions need deterministic backing, such as secret scanning, static analysis, and infrastructure validation. GitHub's responsible-use documentation covers execution isolation, constrained permissions, security scanning, and approval boundaries. It also says agent output still needs review and testing. A common configuration for local agents is deny-by-default with a tight allowlist and explicit denies for risky operations such as network calls. docs.github Stripe's production case shows what isolation looks like at scale. Its system uses isolated development environments and a hybrid of deterministic and agentic steps, with unattended runs followed by human review. GitHub Agentic Workflows takes a similar approach for repository automation. It defines tasks in Markdown with configurable permissions, tools, sandboxing, and controlled outputs, while keeping deterministic CI/CD. stripe Review is the other control point. Osmani argues that a change should arrive with verification evidence, and that human review keeps responsibility for intent, risk, and ownership. Anthropic's guidance on rollouts says the same from the tool side: use test-driven development to give the agent guardrails and clear success criteria. One team playbook adds a simple rule: never let an agent be the sole gate on a merge to protected paths. addyosmani Part 5: Measure what the system delivers The temptation is to count output: pull requests, lines, prompts. Anthropic's playbook explicitly points to measuring ROI beyond vanity metrics. DORA's ROI report offers a framework for managing the initial productivity dip of a rollout and for defending the budget afterwards. I recommend counting accepted changes and the total human effort around them, including planning, supervision, review, and correction. resources.anthropic Be careful with industry statistics. One 2026 guide cites adoption figures and Gartner projections, but those describe adoption, not the return a given team will see. Stripe's weekly merge figure shows that a mature system can work at scale. It is not a forecast for a different organization. coderio Part 6: Keep the counterweights Two sources prevent the enthusiasm from becoming an assumption. HumanLayer's critique argues that harnesses alone do not guarantee long-term codebase quality or shared understanding, and that human steering remains necessary. Fowler's "What Is Code?" argues that clear abstractions, types, and tests make the code itself part of the agent's context and constraints. Both support the same conclusion: agents reward good engineering and expose weak engineering. github Parallel work needs the same caution. Simon Willison's subagent pattern shows how delegation into fresh context windows can separate exploration from implementation. Osmani's guide is a reminder that parallel runs still need agreed boundaries and a single integration owner. simonwillison ------------------ Below is a ranked top-25 reading list, followed by an article that draws on it. The ranking is my own editorial judgment. I weighted practical usefulness for a team, how directly each source is about the source type (official guidance and first-hand case studies over commentary), and coverage across the topics a team has to settle. It is a curated list, not an exhaustive survey. Top 25 reading list | # | Material | Type | Best used for | |---|---|---|---| | 1 | Scaling Agentic Coding Across Your Organization, Anthropic | Official rollout playbook | Pilot, champions, enablement, ROI resources.anthropic | | 2 | Your AI coding agents need a manager, Addy Osmani | Practitioner guide | Delegation and supervision addyosmani | | 3 | DORA: State of AI-assisted Software Development 2025 | Research report | The organizational-system view dora | | 4 | Best practices for using GitHub Copilot to work on tasks | Official guide | Task scoping docs.github | | 5 | Best practices for Claude Code, Anthropic | Official guide | Plan-first workflow, context files code.claude | | 6 | Harness engineering, OpenAI | First-hand case study | Repository knowledge, enforceable constraints github | | 7 | Harness engineering for coding agent users, Böckeler | Architectural analysis | Guidance versus controls beri | | 8 | Minions: Stripe's coding agents, Part 2 | Production case study | Isolation, hybrid workflows stripe | | 9 | Compound Engineering, Every | Open-source workflow | Plan, build, review, learn loop github | | 10 | Humans and Agents in Software Engineering Loops | Engineering analysis | Human responsibility martinfowler | | 11 | AI writes code faster. Your job is still to prove it works | Review guide | Evidence-based acceptance addyosmani | | 12 | Application card: GitHub Copilot Agents | Official responsible-use guidance | Execution controls, limits docs.github | | 13 | The VibeSec Reckoning | Security analysis | Deterministic security checks martinfowler | | 14 | How Claude Code is used in practice, Anthropic | Usage research | Human–agent division of labor anthropic | | 15 | What is Agentic Engineering?, IBM | Vendor explainer | Governance and skills framing ibm | | 16 | Best practices for coding with agents, Cursor | Official guide | Context, rules, iteration cursor | | 17 | Rules, Cursor documentation | Official documentation | Shared, version-controlled rules cursor | | 18 | Writing a good CLAUDE.md, HumanLayer | Practitioner guide | Concise instruction files humanlayer | | 19 | My LLM coding workflow going into 2026, Osmani | Practitioner guide | Incremental workflow github | | 20 | GitHub Agentic Workflows | Open-source implementation | Event-driven automation github | | 21 | Subagents, Simon Willison | Practitioner pattern | Context separation simonwillison | | 22 | BMad Method | Community methodology | Structured planning bmadcode | | 23 | Agentic Coding Playbook, Wilmes | Community playbook | Explore–plan–code–verify github | | 24 | Why Software Factories Fail, HumanLayer | Practitioner critique | Limits of automation-first thinking github | | 25 | What Is Code?, Fowler | Engineering analysis | Maintainability as context martinfowler | Near misses: The Agentic AI Engineering Team Playbook covers roles, RACI, and a 90-day rollout, but it is a vendor-style blog. DORA's ROI of AI-assisted Software Development report is worth reading for budget conversations. digitalapplied

Kaizen: a complete SDLC for Claude Code, from requirement to production A coding agent speeds everything up, mistakes included. Kaizen gives Claude Code a whole development lifecycle, with its critical rules enforced by code. A coding agent writes fast. It also sometimes forgets the tests, or pushes a branch nobody reviewed. The DORA 2025 report measured it: AI raises team throughput, and instability along with it, except in teams that keep clear principles, small batches and real feedback. Kaizen is the plugin I wrote to tool those disciplines in Claude Code, across the whole SDLC, from the requirement to production. It also answers the question I left open in April in my map of SDD, Compound Engineering and BMAD: can you combine the rigor of a spec with a learning loop? > In brief > > - What: Kaizen is an open source (MIT) Claude Code plugin covering the whole development lifecycle: requirements, plan, code, review, PR, deployment, monitoring, postmortem. > - Key numbers: 23 skills, 21 read-only agents, 6 hooks, a Node.js CLI with no npm dependency. Version 3.2.1, October 7, 2026. > - What sets it apart: the critical rules are hooks. Claude cannot finish on red tests, push without a real review, or deploy to production without a code you type. > - Where it comes from: the loop of Every's Compound Engineering, the constitution from Spec Kit, practices from DORA and the NIST SSDF. > - Who it's for: teams on Claude Code that want quality guarantees all the way to production. The SDLC, phase by phase Each classic phase of the cycle has its command. The last column says whether a check in code enforces it. | Phase | Command /kaizen:… | Enforced by code | |---|---|---| | Principles | constitution: 5 to 9 rules, each with a check | partly | | Requirements | brainstorm: requirements R1…, acceptance examples AE1… | partly | | Design | plan (STRIDE threats, rollback, PR-sized slices), then doc-review | partly: plan check verifies every requirement is covered | | Code | work (test first), debug | yes: no end of turn on red tests | | Verification | review, reviewers picked from the diff | yes: push refused without a real review | | Delivery | ship, watch-pr, release | yes: PR size and SemVer checked | | Deployment | deploy with your commands, rollback | yes: approval code for production | | Operations | monitor: plan thresholds, dated incidents | partly | | Improvement | learn, postmortem, metrics (DORA) | partly | Lost along the way? /kaizen:help looks at where the repository stands and gives the next command. The critical rules are hooks Writing "run the tests before finishing" in CLAUDE.md works nine times out of ten. The tenth time the session is long, the context compacted, and Claude reports that all is well over a red suite. So Kaizen puts those rules in hooks, which Claude Code runs on every tool call. - Before a commit, a scan refuses about thirty kinds of keys and tokens. - Before a push, the branch is refused until a review has been recorded, with proof that the reviewer agents really ran. - At the end of a turn, tests, lint and type checks must pass. - For production, only a code you type unlocks the deployment. A loop that learns  This is what Compound Engineering brings. What a cycle learns (learnings, ADRs, postmortems) is written in the repository, and an agent reads it back before every plan, review or debugging session. Deployments, rollbacks and incidents become dated git tags, so the DORA metrics are computed from real events. /kaizen:metrics also separates learnings that were read from those applied in a commit. A learning nobody reuses signals a loop that isn't turning. Ceremony is set by profile: lean for a prototype, standard for a product in production, full for a regulated domain. The checks in code stay on in all three. Try it /plugin marketplace add Lingelo/dojo /plugin install kaizen@dojo Kaizen is built for Claude Code and relies on its hooks. You need Node.js 18 or later, git, and gh for PRs. In your repository, run /kaizen:setup audit: it scores the project's SDLC maturity in five areas and offers to add what's missing. Code and docs are on GitHub. For how plugins work, see my article on Claude Code marketplaces. Frequently asked questions What is Kaizen for Claude Code? Kaizen is an open source (MIT) plugin that gives Claude Code a complete SDLC: requirements, plan, test-first code, multi-agent review, pull request, watched deployment, incidents and learnings. It ships 23 skills, 21 read-only agents and a zero-dependency Node.js CLI. Version 3.2.1 was released on October 7, 2026. What is an AI SDLC? An SDLC (Software Development Life Cycle) is the set of phases that take software from a requirement to production: framing, design, code, verification, delivery, deployment, operations and improvement. An AI SDLC tools those phases for a coding agent, with checks suited to a fast executor that can forget an instruction. How is Kaizen different from Compound Engineering? Kaizen is derived from Every's Compound Engineering plugin (MIT) and keeps its learning loop. It adds checks enforced by hooks, Spec Kit's constitution, deployment, monitoring and DORA metrics. Kaizen is built for Claude Code and relies on its hooks. How do I install Kaizen? In Claude Code, add the marketplace with /plugin marketplace add Lingelo/dojo, then install the plugin with /plugin install kaizen@dojo. Kaizen needs Node.js 18 or later and git, plus gh for pull requests. In a repository, start with /kaizen:setup. Can Kaizen deploy to production on its own? No. Kaizen only deploys with the commands the team declared, and for a protected environment the user must type an approval code, valid for 30 minutes. Autopilot mode stops at a ready pull request and never merges or deploys. --- Originally published on angelo-lima.fr.

we (@ArielleShipper) made the ultimate set of skills for running an automated hiring pipeline in Codex available for on the @every github: EveryInc/every-hiring-automations-kit-public t.co