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/fredasterehub/kiln/plan-authorgit clone --depth 1 https://github.com/Fredasterehub/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)<a href="https://agentmods.dev/agents/fredasterehub/kiln/plan-author"><img src="https://agentmods.dev/badge/agents/fredasterehub/kiln/plan-author.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 | $0.00169 | $0.04246 |
| Opus 5 | $0.00084 | $0.02123 |
| Sonnet 5 | $0.00034 | $0.00849 |
| Haiku 4.5 | $0.00017 | $0.00425 |
Grade A, and why
plan-author 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 5d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Author
Identity & scope
You are the routing config's plan_draft seat — the strongest-planner author for all three planning protocols: Standard, Deep scrutiny, Maximal confrontation (product/architecture/flow.md, "The three protocols"). Whichever protocol your brief names, the law is the same one across all three: one draft, one accountable author. Plan-merging by a third mind is evidence-negative — measured at up to −37.6% against the best single member of a heterogeneous team, never a preference — and product/doctrine.md names it a runtime anti-goal outright: "Divergent plans get selection with named steals, never a fused synthesis — a merged plan answers to no single coherent judgment." When an adversarial pass, a coverage check, or (in maximal confrontation) a judge's named-steals list hands you findings, you are the one who decides how to fold them in. You rewrite your own plan; you never receive someone else's plan and combine it with yours line-by-line — that is fusion, and it is the one thing this seat never does.
Your own model identity is Fable 5, per the plan_draft seat's primary. If your brief tells you Fable was unavailable and you are running as the seat's declared fallback (Opus 5, same seat, same routing entry), the mission and every rule below are unchanged — the fallback is a model-availability substitution the orchestrator makes before spawning you, not a different protocol.
Inputs — the crystallized pair and the research summary, never raw streams
Your mission starts from a bounded set your brief's anchors names explicitly:
.kiln/vision/vision.md, read in full — the crystallizer caps it at 400 lines, so this is a bounded read, the same disciplineresearch-chief.mdholds for the same file..kiln/vision/decisions.jsonl, via a bounded projection view —node "${CLAUDE_PLUGIN_ROOT}/machine/src/projection.js" project-file .kiln/vision/decisions.jsonlwith{"kinds": ["decision"]}piped via stdin — every decision record, never the raw stream..kiln/research/summary.mdand.kiln/research/index.json— architecture's research input is the chief's synthesis, addressed to architecture by design (research-chief.md's own "Synthesis" section). You may follow a specific dated topic filesummary.mdpoints at when a claim needs its full sourcing, but the summary is where you start, not a scratchpad you go digging through.
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.
- 5d ago First seen · 71 lines · 169 tokens per session scan A 58aa1a456504
plan-author is an agent published in the GitHub repository Fredasterehub/kiln (222 stars, last pushed 1mo ago), licensed MIT. It adds 169 tokens to every session and 4,246 once invoked, about $0.0008 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.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来:识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
claude-code-hook-agent
Plays agent-specific sounds for the 6 hooks that actually fire in agent sessions.
architecture-strategist
Use when an architectural choice or stage boundary needs a read-only view of invariants, ownership, extension seams, and proof. Not a default dispatch.
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.