mir-init

Solid

Make It Right (project init). Prepares a repository's Make It Right harness before feature work starts: detects the stack from lockfiles, confirms it through a deterministic picker (never guesses), resolves the matching mir-* skills, and generates the per-project artifacts — a thin AGENTS.md that names the applicable pillars, a CLAUDE.md that imports it, a .mir/manifest.json write policy, and a .claude/settings.json PreToolUse hook that enforces it — then runs a manifest-derived probe to prove the hook actually blocks the denied paths. It is a thin wrapper over the CLI at init/cli.py; it installs no software and generates no code. TRIGGER when a user is setting up a new or existing repo for AI coding agents, asks to 'prepare/scaffold/bootstrap the harness', to generate AGENTS.md/CLAUDE.md/hooks, or to choose and lock a stack. SKIP for writing feature code (that is the backend/frontend/mobile pillars and their gated pipeline), for one-off task constraints (the constraint-interrogator handles those at Gate 1),

AI & Automation 15 stars 0 forks Updated 1 weeks ago Apache-2.0

Install

View on GitHub

Quality Score: 81/100

Stars 20%
40
Recency 20%
90
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# /mir-init · Make It Right (project init) Prepare a repo's harness once, before feature work. This skill drives the CLI; it does not reimplement it. The CLI lives at `init/cli.py` in the make-it-right repo (or run `bin/mir`). ## What it does, in order 1. **Detect.** Read `package.json`, `go.mod`, `Cargo.toml`, `requirements.txt`, `pyproject.toml`, `Gemfile`, `composer.json`, `mix.exs`, `*.xcodeproj`. Detection **proposes** with "detected X because Y" and a confidence; it never silently decides. Two frameworks in one pillar is a conflict you must resolve, not a guess. 2. **Confirm through the picker.** The options are derived from the installed skill tree, so they are always in sync with what exists. Present them with `AskUserQuestion`; pre-fill the detected answers. A stack with no skill is an explicit "Something else" choice — recorded as a gap, never dropped. Do not let the user skip a genuinely ambiguous or high-stakes choice. 3. **Resolve** the answers to the coarse→fine skill set (pillar → tier → module), with `mir-devsecops` always included (security by default). 4. **Generate** the artifacts (see below). `--dry-run` prints the plan and writes nothing. 5. **Verify.** Run `.mir/probe.py` against the generated guard. The probe derives its attacks from the manifest and includes positive controls, so a missing or broken guard fails loudly instead of reading as "everything blocked." ## Run it ```bash python3 init/cli.py init . # or...

Details

Author
anantbhandarkar
Repository
anantbhandarkar/make-it-right
Created
3 months ago
Last Updated
1 weeks ago
Language
Python
License
Apache-2.0

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Solid

mir-backend

Make It Right (backend pillar). Constraint-first backend planning protocol for AI coding agents — AI makes code that WORKS on the happy path; this makes it RIGHT under concurrency, failure, and load. Forces the model OUT of pattern-completion ('autocomplete from latent space') and INTO explicit constraint discovery before any code is written. Use whenever a task involves backend logic that changes state, touches money/inventory/auth, spans multiple tables or services, runs under concurrency, or persists data beyond a single request. Runs a hard-gated pipeline: Intent → Constraint Interrogation → Assumption Ledger → Invariants & Failure Modes → Risk Register → Design Review → Implementation → Production-Readiness Review. Spawns specialized reviewer sub-agents. Chains into a runtime tier (e.g. mir-backend-python for CPython concerns) and a framework module (e.g. mir-backend-python-fastapi for FastAPI/SQLAlchemy/Alembic). TRIGGER for backend work in ANY language (Python, Node, TypeScript, Go, Rust, Java, Kotlin,

15 Updated 1 weeks ago
anantbhandarkar
AI & Automation Listed

init-harness

One-shot initialization of a parallel-terminal Claude Code build harness in a project - a git worktree and branch per terminal, phase checkboxes as the task queue, pinned model/effort per agent, mechanical git-tag gates, hardened read/gate/log hooks, and a SQLite agent-memory shard per terminal. Use when the user says "/init-harness", "init-harness", "initialize the harness", "set up the build harness", "scaffold this project's harness", "bootstrap the agent harness", or drops in a project-context.yml and asks to initialize. Also use when a project needs multi-terminal agent orchestration with gates, or when an existing harness must be verified or repaired (hooks not firing, guards not blocking, .agents drift). Do NOT use for adding a single agent or skill to an existing project.

1 Updated 1 months ago
M4NUSH7
AI & Automation Listed

init

Set up this SDD harness in a project — detect the toolchain, interview for what cannot be inferred, and write .steering, .specs, .work_logs, a project-specific reviewer, and the hooks. Use once per project, or to migrate a project that already has parts of the harness.

0 Updated today
m0m0i