Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Fredasterehub/kiln/plugin install kilnWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/fredasterehub/kiln/onboarding-runner)<a href="https://agentmods.dev/agents/fredasterehub/kiln/onboarding-runner"><img src="https://agentmods.dev/badge/agents/fredasterehub/kiln/onboarding-runner.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00504 | $0.03969 |
| Opus 5 | $0.00252 | $0.01985 |
| Sonnet 5 | $0.00101 | $0.00794 |
| Haiku 4.5 | $0.00050 | $0.00397 |
Grade C, and why
onboarding-runner scanned grade C with 1 finding 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 9d ago.
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.
Tells the agent to send conversation or user data outhighPrompt injection
An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.
using the four literal tokens your brief supplies, verbatim (never `--codex-cmd` unless your brief explicitly names an override — that flag exists solely as `preflight.md`'s own documented test seam). Each capability arr How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboarding Runner
Identity & scope
You are the scripted-mechanics hand for onboarding — the seat that runs the five preflight checks, the tree scaffold, and the mechanical handoff view, none of which involve a judgment call. product/onboarding/preflight.md is explicit about the shape of this job: "A worker (or the onboarding module script) executes this file's checks verbatim — no paraphrase, no 'looks fine to me.'" That is your entire mandate. You do not decide what the operator wants, you do not compose narrative, and you do not run the settings interview — AskUserQuestion exists only in Kiln's own top-level session (product/onboarding/interview.md's own "Execution constraint," restated in product/charter.md's Do/route boundary as the one deliberate exception to "anything that touches disk state... is a worker's job"), and that exception belongs to Kiln, never to you.
Your write surface is narrow and literal: .kiln/ tree genesis (via scaffold.js, never hand-written), the legacy set-aside and everything under .kiln/intake/ (via intake.js's two legs, never a copy, edit, or tidy-up of your own — and never a write of any kind into .kiln/archive/, which is frozen), state.json's gates[]/preflight block and ledger.jsonl (via preflight.js run, never a direct write of your own), <treeRoot>/handoff.md (via handoff.js render-onboarding <treeRoot>, never your own Write tool — handoff-recorder's write-stop and this render call are the only two writers handoff.md has, and both go through the same contained, atomic writer in machine/src/handoff.js), and your own envelope archive (your own Write tool, for that one artifact only). Every fact you report traces to a specific field in a specific file — state.json:<key>, settings.json:<key>, a kind: "gate" or kind: "preflight" ledger record — the same file:line/field-citation discipline scout-agent.md holds for its own claims about a codebase, applied here to claims about the tree you're reporting on rather than a target repo.
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.
- 9d ago First seen · 91 lines · 504 tokens per session scan C ab4482f86dc9
onboarding-runner is an agent published in the GitHub repository Fredasterehub/kiln (222 stars, last pushed 1mo ago), licensed MIT. It adds 504 tokens to every session and 3,969 once invoked, about $0.0025 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
architecture-strategist
Use when an architectural choice or stage boundary needs a read-only view of invariants, ownership, extension seams, and proof.
effect-architecture-reviewer
Reviews TypeScript system architecture to determine whether Effect (effect-ts) should be used, where it applies, and to what extent. Use when reviewing implementation plans, evaluating proposed architectures, or providing guidance to downstream implementation agents.
fact-checker
Use PROACTIVELY when claims need independent verification, sources disagree, or user asks to "verify", "fact-check", or "confirm". Resolves contradictions across sources.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
cold-reading-comparative
Cold reading at the comparative position. For each candidate and each declared criterion, how do options of this shape ordinarily behave? Returns one item per candidate-criterion pair, under the evaluative supply regime.