The 11-Stage Software Factory.
The factory does not write the code itself. Your agent writes it; VibeHard pours the structural foundation around it. It takes a plain-English request, asks about what is unclear, plans it in writing, has the plan audited, waits for your sign-off, and builds it slice by slice. Then it runs a 44-gate verification chain and a separate build audit before it stamps .gate/HARD_VERIFY_PASS.
Skips discovery, rebuilds components that already exist, and grades its own work.
Every stage leaves a record, from your answers at intake to the sealed plan, the gate verdicts and the build audit.
The 11-Stage Manufacturing Pipeline
ACTIVE TRACK: [01] Custom Software Factory (44 Gates · Slice-by-Slice Build · Repair Loop · Build Audit)
Intake & Questions
Your agent hands the factory a plain-English request. Where the request is ambiguous, the factory asks instead of guessing. On the strictest setting, questions about security, data, who can access what, payments or compliance must be answered by a person, not the agent.
Reference Analysis
Point the factory at a product you want to match or replace. It records each reference capability and decides what to keep at parity, modernize, improve or drop, so nothing is lost by accident.
Buy Before Build
Before any custom code is planned, the factory looks for proven components that already do the job, and records each buy-or-build decision. A later gate checks that the build honored those decisions.
The Planning Documents
Writes the spec, product requirements (PRD.md), system requirements (SRS.md), system architecture (SAD.md), architecture decision records, assumptions, a red-team brief and a build plan.
Planning Audit
Three independent review lenses (skeptic, architect and minimalist) audit the plan before a line of code is written. Findings go back into the plan.
Your Sign-Off
Scope review and plan approval are recorded checkpoints. The build waits for your answer, and a changed plan comes back to you for approval.
Plan Seal
The approved plan is sealed: a SHA-256 digest of the planning documents and the starting code tree, recorded before any code is written.
Slice-by-Slice Build
Your agent writes the code one slice at a time, from work orders the factory issues and checks. Backends for TypeScript, Go, Rust, Python and Elixir; the 2.0.1 acceptance run exercised TypeScript.
Repair Loop
When a check fails, the factory sends your agent the full failure output (both output streams, new in 2.0.1), takes the fix and runs the checks again, up to ten attempts.
The 44-Gate Chain
Security, quality, contract and operations gates, fitted to the project: a gate that does not apply reports n/a instead of a fake pass. Only a full pass writes the sealed pass marker.
Build Audit & Handoff
The same three lenses audit what was actually built. The factory writes an as-built report, updates the README and architecture docs, and hands the finished project to you.
The 44-Gate Verification Chain
Before a build is marked done, it passes through a chain of 44 gates covering security, quality, API contracts and operations. Almost all are fixed, rule-based checks; the completeness gate has a reviewer compare the finished features against the spec. The chain is fitted to the project: a command-line tool skips database gates, and a project with no Rust skips the Rust gates. A gate that does not apply reports n/a instead of a fake pass. See every gate.
Buy Before Build
Checked by a GateA well-run factory prunes bloat before it builds anything. During planning, the factory records which proven components to adopt instead of writing them again, and which capabilities from a reference product to keep, modernize, improve or drop. After the build, a gate checks that the code honored those decisions.
Proof, Not Promises
Version 2.0.1 passed our official acceptance run: one run, no retries, built from a frozen spec. The job completed, 0 of 44 gates blocked, the build audit accepted it, and all three output fixtures matched byte for byte. Twelve gates passed; the other 32 did not apply to that small command-line project. A separate reviewer re-checked the evidence and confirmed the result. What it does not show: in that run the plan approvals came from the test harness, not a person, and a test agent drove the build. It verifies the factory code; it does not certify the downloadable build, which is built and signed separately.