Pick the components you need.

For model-free repository checks, start with captured doctrine audits and comparison. JARVIS is an optional policy-governed executor.

You don't need all of PRISM. Every component is small, independent, and composable — a Bun-built dist/*.js bundle sharing one runtime. Start from your goal, install the minimal set, add more later. All live on the sovereign forge at git.sovereign-society.org/prism.

The components, in detail

Each one answers: what do I get?

Install Browse the forge ↗

The scrub subcommand — GitSpawn-class defense

Every PRISM CLI exposes a scrub subcommand that removes dangerous git-config keys (core.fsmonitor, core.hooksPath, core.sshCommand, filter.*.clean/.smudge, and adjacent command-execution vectors) from the LOCAL .git/config of a target. Defense for the Sept 2026 wave of malicious-repo payload attacks. Full writeup →

# 1. Scrub BEFORE opening any untrusted repo in an AI agent.
prism-harness scrub /path/to/untrusted-repo
# 2. Audit (CI gate, supply-chain check).
prism-harness scrub --dry-run --json /path/to/repo | jq .
# 3. Same surface on every other CLI:
prism-graf scrub ~/projects/maybe-hostile
prism-loop scrub ~/projects/maybe-hostile
prism-sober scrub ~/projects/maybe-hostile
prism-route scrub ~/projects/maybe-hostile
prism-proxy scrub ~/projects/maybe-hostile

Every PRISM CLI that touches a repo also auto-scrubs before any git call — prism-harness init, prism-graf init, prism-loop doctor, prism-route smoke, prism-proxy smoke. Fail-closed: if the scrub reports errors, the CLI exits 1 without touching the repo.

What the agent reads

The CLIs are small, but together they enforce twelve markdown rules and ship dozens of templates. On every session start, the visiting AI agent reads the doctrine at agents/rules/*.md first. That reading is what stops AI-slop:

• Repo firewall — public/private boundary discipline.
• Atomic forge cycle — every change is a complete, verifiable step.
• Panopticum — one feature, one folder, one index.
• TDD commit validation — no test, no commit.
• SDD/BDD ordering — EARS for rigor, Gherkin for walkthrough.
• Git worktree workflow — branch, worktree, rebase, push gates.
• OpenSpec naming — v001- changesets, c001- capabilities, gapless sequences.
• Crypto quality — cryptographic work without vectors is speculation.
• SAP future-proofing — adapters over hard-coded SAP.
• Customer disclosure — public/private content boundaries.
• Agent execution — read context → identify slice → test → implement → verify → report.
• Goals — primary goal + current priority + decision rule.

Path conventions — non-overlapping

your-project/agents/{rules,templates,scripts,...}      ← doctrine (per repo)
your-project/.prism/{blueprint,ledger,heartbeat,...}    ← loop memory (per repo)
your-project/.graf/                                     ← graf object store (per repo)
~/.prism/identity/*.md                                  ← agent identity (per user)
~/.sober/steering/*.md                                  ← Sober-Raccoon (per repo)
~/.config/containers/systemd/prism-*.container         ← container (per host)

Each tool owns its own surface. No path overlap. Each tool has a sovereign index.

Model + services first

The installer prompts component selection in priority order: model + services (prism-route) first, plugins after. Without prism-route the identity canon has nothing to talk through. Without prism-sober the doctrine is unverifiable. Without prism-loop the agent forgets by morning. Each adds a layer. And prism-chat hands the same gateway to the human directly — a terminal and a PWA, no agent in the loop. prism-graf gives multi-agent operators a sovereign VCS with lane discipline; JARVIS SPEC-028 is the runtime adapter that hires specialists onto those lanes. And prism-mem closes the loop that matters most over months: what your agents establish becomes signed, portable knowledge your configured future sessions can retrieve — the portable brain.