AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Develop Like 37signals

skill-marcusrbrown-dev-like-develop-like-37signals · by marcusrbrown

>-

No reviews yet
0 installs
16 views
0.0% view→install

Install

$ agentstack add skill-marcusrbrown-dev-like-develop-like-37signals

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-marcusrbrown-dev-like-develop-like-37signals)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
23d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Develop Like 37signals? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Develop like 37signals

> Profiled as of 2026-07-16 · consent tier: self-published · full bibliography in [references/sources.md](references/sources.md). Cultures drift — if this is more than ~6 months old, re-run /dev-like 37signals to refresh.

Core principle

Fixed appetite, variable scope — decide how much time a problem is worth before you decide what to build, then build to that budget instead of estimating a spec [[Shape Up ch.1]](https://basecamp.com/shapeup/0.3-chapter-01). Work happens in six-week cycles with a two-week cooldown between them, and all teams share the same cadence [[how we work]](https://github.com/basecamp/handbook/blob/master/how-we-work.md).

Principles

  1. Fixed appetite, variable scope — decide the time budget before the solution [[Shape Up ch.1]](https://basecamp.com/shapeup/0.3-chapter-01)
  2. Six-week cycles with a two-week cooldown, no exceptions across teams [[how we work]](https://github.com/basecamp/handbook/blob/master/how-we-work.md)
  3. No backlogs — shape and bet, don't queue [[Shape Up ch.8]](https://basecamp.com/shapeup/2.2-chapter-08)
  4. Hand over whole projects, not task lists; done means deployed [[Shape Up ch.10]](https://basecamp.com/shapeup/3.1-chapter-10)
  5. Circuit breaker — cancel by default rather than extend a project past its cycle [[Shape Up ch.8]](https://basecamp.com/shapeup/2.2-chapter-08)
  6. Show progress on a hill (uphill/downhill), not with estimates or percentages [[Shape Up]](https://basecamp.com/shapeup)
  7. Vanilla Rails, server-rendered, minimal dependencies — fight hard before adding a gem or a JS package [[vanilla Rails stack]](https://dev.37signals.com/a-vanilla-rails-stack-is-plenty/)
  8. Manual, guided exploratory QA over exhaustive test-case matrices [[all about QA]](https://dev.37signals.com/all-about-qa/)
  9. Coding is craft, not overhead to delegate away — pair with AI, don't hand it the keyboard [[coding should be a vibe]](https://world.hey.com/dhh/coding-should-be-a-vibe-50908f49)

Workflow

Shaping (defining the problem, appetite, and rough solution) happens ahead of the cycle; bets are placed at a betting table during cooldown, not pulled from a backlog — "no backlogs" is explicit doctrine [[Shape Up ch.8]](https://basecamp.com/shapeup/2.2-chapter-08). A team that takes a bet owns the whole project, not a list of tasks, and "done means deployed" [[Shape Up ch.10]](https://basecamp.com/shapeup/3.1-chapter-10). Progress is tracked with hill charts (uphill = unsolved, downhill = just execution) instead of percent-complete or burndown [[Shape Up]](https://basecamp.com/shapeup). A circuit breaker cancels projects that don't ship within their cycle by default, rather than auto-extending them [[Shape Up ch.8]](https://basecamp.com/shapeup/2.2-chapter-08). Cooldown is when bugs get fixed, cycles get planned, and the next bets get made [[how we work]](https://github.com/basecamp/handbook/blob/master/how-we-work.md). QA is a two-person team running manual, guided exploratory testing against ~100-item per-product checklists (not exhaustive test-case matrices), plus accessibility passes with screen readers and a home-grown BackstopJS visual-regression suite [[all about QA]](https://dev.37signals.com/all-about-qa/).

See [references/stack.md](references/stack.md) for the stack and [references/workflow.md](references/workflow.md) for workflow detail.

Tensions

  • Manual QA is a deliberate, celebrated practice — two people running guided exploratory

passes and checklists, not automated end-to-end suites [[all about QA]](https://dev.37signals.com/all-about-qa/). That's a real bet against TDD/heavy-automation dogma; it works because their QA staff are experienced generalists embedded in the Shape Up cycle, not because automated testing doesn't matter — Minitest and fixtures are still standard practice in the stack [[vanilla Rails stack]](https://dev.37signals.com/a-vanilla-rails-stack-is-plenty/). Don't read "manual QA works for them" as "skip your test suite."

  • AI posture is genuinely split by voice and by time. DHH is on record wanting to keep his

hands on the keyboard and treating full vibe-coding handoff with suspicion [[coding should be a vibe]](https://world.hey.com/dhh/coding-should-be-a-vibe-50908f49), while a year later the company shipped a fully agent-accessible Basecamp — revamped API, CLI, and a bundled skill for agent harnesses [[agent-accessible]](https://world.hey.com/dhh/basecamp-becomes-agent-accessible-3ae6b949). Mimic the trajectory (cautious about full autonomy in the editor, enthusiastic about making the product agent-operable), not a single fixed stance.

  • Shape Up's six-week/two-week cadence assumes a company that can hold "all teams operate on

the same 6-week cadence" [[how we work]](https://github.com/basecamp/handbook/blob/master/how-we-work.md) — a ~70-person, cross-functional, deeply synced org. It doesn't obviously survive contact with much larger or less disciplined organizations without adaptation, which the book itself acknowledges (Appendix: "Adjust to Your Size") [[Shape Up]](https://basecamp.com/shapeup).

Want a reviewer/pair persona in 37signals's voice? See [personas/37signals-developer.md](personas/37signals-developer.md) — it's reference material. Claude Code users can copy it to .claude/agents/ to run it as a first-class subagent; other harnesses may need their own harness-specific metadata.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.