Daily Edition Sources +6

Builder Work: Mycelium Makes Agents Prove The Product Before Coding

Haabe's Mycelium is an open-source Claude Code plugin that was publicly described as built using itself and repo-inspected as a decision framework with receipts, git-stored state, and agent skills.

Rough zine-style diagram showing Mycelium evidence cards for built using itself, decision scales, YAML in git, and receipts feeding discovery before delivery.
Diagram PunkMycelium makes the agent earn the build before it codes.
repos source trail evidence
6 source signals 0 repos 6 source signals
Evidence: 6 source signals / July 6, 2026 / Daily Edition
Open Edition Evidence below

The scout source is a July 4 Show HN post for Mycelium, where the builder describes a coding-agent plugin that starts upstream of implementation and says the project is being dogfooded on itself. The repository README makes the proof sharper: "Built using itself" appears in the public project description, beside Claude Code install commands and a receipts index.

This is not a five-minute wrapper because the repo is mostly governance machinery, not a single prompt. Its docs define Purpose, Strategy, Opportunity, Solution, Delivery, and Market scales; its skills guide the agent through discovery and evidence checks; and its receipts record cases where the framework changed after user runs found weak assumptions.

The Craft

The building skill worth borrowing is to make the agent's pre-code discipline durable. Mycelium stores product decisions as plain YAML in the repo, requires evidence before advancing, and treats a failed check as a loop back to discovery rather than as a blocked build.

Repo Receipts

The README points to install paths, usage modes, skills, theory grounding, an AI system card, and a receipt index. One receipt says a recurring pattern across five instances became a standing self-check; another says a dead-link sweep missed prose/code-span path rot, leading to a second guard.

Reader Takeaway

Builders using coding agents can copy the shape even without the plugin: put the riskiest assumption in the repo, force the agent to name the smallest test, and preserve the decision record where future sessions can read it.

Caveat

The public evidence proves an early open-source framework and its self-reported dogfooding, not broad adoption or outcome quality. Constructive follow-up: publish one complete anonymized run from prompt to YAML decision to shipped or rejected build.

Evidence Trail

Receipts below the story

The article above is the public narrative. This section keeps the source trail and limits on the same page.

Edition
DateJuly 6, 2026
LaneDaily Edition
Confidence87%
Sources6
Repossource trail

Primary Evidence

Evidence Limits

  • The sources prove public coding-agent use and repo structure; they do not prove broad adoption, product-market fit, or outcome quality.
  • The article treats dogfooding as public self-reported proof and asks for a complete public/anonymized run as a constructive next step.
Letters & Corrections

Send a note to the desk

Corrections, missing context, or a follow-up lead.