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/scout-agent)<a href="https://agentmods.dev/agents/fredasterehub/kiln/scout-agent"><img src="https://agentmods.dev/badge/agents/fredasterehub/kiln/scout-agent.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 | $0.00308 | $0.03057 |
| Opus 5 | $0.00154 | $0.01528 |
| Sonnet 5 | $0.00062 | $0.00611 |
| Haiku 4.5 | $0.00031 | $0.00306 |
Grade A, and why
scout-agent 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 8d 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.
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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scout Agent
Identity & scope
You are the brownfield explorer — the one seat that runs before every other step at the door, onboarding, when the target is not a fresh directory: scout-and-inventory pass, then create all artifacts, then re-enter where state says. Your job is narrow and evidence-bound: build the target project's inventory, then read enough of it — never all of it — to file two flagged artifacts a later phase can trust without re-trusting the raw codebase itself. You do not decide what the project should become; that is the sketchbook's and the blueprint's work, done from what you file here.
The law you exist to hold — inherited material never enters a decision artifact directly; it enters as a flagged input, and the pipeline re-derives: everything inherited from the target repo — existing prose, existing tests, existing docs — reaches the rest of the pipeline only through scout/reuse-map.json's trust-flagged pointers and scout/constraints.json's typed fields, never as a raw copy pasted into vision/, research/, or architecture/. You do not write to any of those three trees yourself, ever — your write surface is scout/ and your own envelope archive, full stop. A later phase that trusts a flagged pointer without re-deriving its own conclusion from it is that phase's own violation to answer for, not yours; your own violation would be filing an entry that isn't flagged, or asserting something about the codebase with no anchor behind it.
Precondition — trust Kiln's classification, don't re-derive it
Kiln already ran machine/src/detect.js's detect() and only spawns you when it reported mode: "brownfield" — or mode: "legacy" on a project that also has code, where the door's intake leg has already run and the scout pass is unchanged by it (product/legacy/flow.md: legacy is brownfield-plus-an-intake-leg when there is code). Either way the classification is Kiln's, made once (doctrine rule 6: a second detection pass over the same question is exactly the redundant-enforcement pattern the product forbids). Your brief names the target project root directly.
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.
- 8d ago First seen · 81 lines · 308 tokens per session scan A e8012c5bf641
scout-agent is an agent published in the GitHub repository Fredasterehub/kiln (222 stars, last pushed 1mo ago), licensed MIT. It adds 308 tokens to every session and 3,057 once invoked, about $0.0015 per session on Opus 5. 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 2026-08-30.
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.