Is moradin-build safe to install?

SaferSkills independently audited moradin-build (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

100

35.0 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 0 flagged

Securityscore 100 · 0 findings

✓—All security checks passedNo findings in this category for the latest scan.pass

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

skills/build/SKILL.md · 1 file

skills/build/SKILL.md2.1 KB · Markdown

name: moradin-build

description: Structured build session against a target project. Apply Moradin's principles + patterns to a real task.

moradin:build

Run a structured build session. The workshop's core verb.

When invoked

/moradin:build <project> <task>

Example: /moradin:build godtech "add a worker harness to Life Agent"

What you do

Load context from Moradin:

Read memory/_INDEX.md to see what's available
Read memory/principles/ (the universal rules)
Read relevant memory/patterns/ (by topic — for harness task, load patterns tagged harness)
Read memory/references/ if external knowledge is relevant

Load context from target project:

Read projects/<project>/state.md — current architecture summary
Read <target-project-path>/CLAUDE.md or AGENTS.md — the project's own context
Read the specific files relevant to the task

Propose a plan. Reference the patterns + principles you'll apply by file path. Don't just say "I'll add a harness" — say "I'll apply memory/patterns/harness_contract.md to add a worker harness following the 5-step closed loop."

Wait for operator approval before executing. Show the plan, ask for go/edit.

Execute — edit the target project's files (NOT Moradin's files, unless explicitly capturing a new pattern that emerged).

Write a session log at projects/<project>/sessions/<YYYY-MM-DD>_<topic>.md:

What was the task
What patterns/principles were applied
What files changed
What worked, what was tricky

Don't

Don't edit Moradin's memory/ during a build session (unless capturing a new lesson via /moradin:ship).
Don't skip reading the target project's CLAUDE.md — that's the runtime truth.
Don't apply patterns blindly. Verify each pattern actually fits the specific task.
Don't execute without operator approval of the plan.

Output

Files changed in the target project
New session log at projects/<project>/sessions/
Optionally: updated project state.md if architectural state changed

moradin-build— agent skill

Is moradin-build safe to install?

moradin:build

When invoked

What you do

Don't

Output

Audit the pieces. Scan the whole. Decide.