Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/callstackincubator/rozenite/validationgit clone --depth 1 https://github.com/callstackincubator/rozeniteWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.01197 |
| Opus 5 | $0.00000 | $0.00598 |
| Sonnet 5 | $0.00000 | $0.00239 |
| Haiku 4.5 | $0.00000 | $0.00120 |
Grade A, and why
validation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validation
How to run checks in this repository without rebuilding all 38 packages for a two-file change.
Commands
Prefer the :affected variants. They diff against the base branch and run only
the packages your change actually touches, plus their dependents.
| Purpose | Command |
|---|---|
| Typecheck + lint + format | pnpm checks:affected |
| Tests | pnpm test:affected |
| Individual tasks | pnpm typecheck:affected, pnpm lint:affected, pnpm build:affected |
For a typical pull request, both of these together are the expected validation:
git fetch origin main
pnpm checks:affected && pnpm test:affected
Use the :all variants (pnpm checks:all, pnpm test:all) only when the change
is genuinely repo-wide — a release, or an edit to a root config file such as
tsconfig.base.json, eslint.config.mjs, or pnpm-workspace.yaml.
The base branch ref must exist locally
--affected compares against the base branch. If that ref is missing — common in
a fresh worktree or a shallow clone — Turborepo silently treats every package
as affected and does the expensive thing anyway. Fetch it first:
git fetch origin main
CI does the same thing (see the "Fetch base branch" step in
.github/workflows/ci.yml) and sets TURBO_SCM_BASE explicitly.
The Turborepo cache is already shared between worktrees
Turborepo detects git worktrees and points them all at the main checkout's
.turbo/cache (Using shared worktree cache in turbo --dry/-vv output), so
a new worktree does not start cold. Do not set TURBO_CACHE_DIR to work
around a problem that does not exist; the cache key is content-based, so
identical code hits the cache from any worktree.
TURBO_CACHE_DIR is only useful for a genuinely separate clone, which does not
share the main checkout's .turbo.
Task output is quiet by default
turbo.json sets outputLogs so that successful, cached work stays quiet:
build and typecheck print only on failure, lint and test print on real
runs but not on cache replays. Failures always print in full. To see everything,
put the flag on the turbo command itself — passing it through pnpm run would
forward it to ESLint instead:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 106 lines · 0 tokens per session scan A 8b7dcd28a592
validation is an agent published in the GitHub repository callstackincubator/rozenite (653 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,197 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
debugger
Debugs errors, test failures, and unexpected behavior. Knows PromptScript architecture.
worktree-collaboration
This document defines the default collaboration protocol for multiple Agents working on Vibelution in parallel.
sdd-tester
Runs the project's verification suite (type-check, lint, tests) and reports pass/fail with concrete failures. Use AFTER the implementer finishes a task and BEFORE the verifier. Read-only on source. Stack-agnostic — reads the commands from .memory/30-tech.md.
issue-tracker
Predict issues and PRDs live in Consensys Jira.
domain
This document defines the canonical domain language for Vibelution so architecture work can use stable names for the same concepts. It is intentionally small: add terms when they become load-bearing in design or tests.
sdd-planner
Breaks a feature spec + design into atomic, ordered, testable tasks. Use AFTER spec.md and design.md exist and AFTER the researcher's report. Writes specs/ /tasks.md. Stack-agnostic.