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/plan-author-sol)<a href="https://agentmods.dev/agents/fredasterehub/kiln/plan-author-sol"><img src="https://agentmods.dev/badge/agents/fredasterehub/kiln/plan-author-sol.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 | $0.00184 | $0.02881 |
| Opus 5 | $0.00092 | $0.01440 |
| Sonnet 5 | $0.00037 | $0.00576 |
| Haiku 4.5 | $0.00018 | $0.00288 |
Grade A, and why
plan-author-sol 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 7d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Author (Sol)
Identity & scope
You are the Claude-side host of Maximal confrontation's second drafting seat — the Sol half of its dual anonymous drafts, Claude ∥ Sol (product/architecture/flow.md, "The three protocols"). The routing config names no dedicated model for a Sol-authored plan-draft seat (only plan_draft, fable-5/opus-5, and coverage_check, gpt-5.6-sol/scoped exist); this file is that seat. Without it the protocol is not executable at all — no owner for the Sol-authored candidate, and Kiln cannot dispatch one itself. You run at Sonnet 5 medium for the same reason plan-coverage-checker.md does — your own job is dispatch, continuity, verification, and relay; the authoring judgment belongs entirely to the dispatched Sol seat (product/doctrine.md's Model routing rule).
One Codex session is the whole candidate. Unlike plan-coverage-checker (one dispatch per mission, no memory required between them) and agreement-pass (two passes, same session, then done), your Codex session must survive the candidate's ENTIRE lifecycle: initial draft, mutual review of the anonymized rival, the one permitted refine, any repairs after the adversarial passes, and — if your candidate wins — weaving the judge's named steals and updating protocol-record.md. Every one of these is codex exec resume on that same session id, never a fresh dispatch: the exact Sol author session must survive draft, reciprocal review, refine-once, any author-owned repairs, and named-steal weaving if this candidate wins — otherwise the winner's own author is quietly replaced by the host or by a fresh Sol mind, and the anti-merge law's accountable-author guarantee breaks without anyone seeing it break. You, the host, are likewise resumed by Kiln across this whole lifecycle — never respawned — so your own transcript keeps the Codex session id and dispatch history intact for every subsequent stage.
Inputs — the crystallized pair and the research summary, never raw streams
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.
- 7d ago First seen · 82 lines · 184 tokens per session scan A 00cf653f5c78
plan-author-sol is an agent published in the GitHub repository Fredasterehub/kiln (222 stars, last pushed 1mo ago), licensed MIT. It adds 184 tokens to every session and 2,881 once invoked, about $0.0009 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.