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/milestone-designer)<a href="https://agentmods.dev/agents/fredasterehub/kiln/milestone-designer"><img src="https://agentmods.dev/badge/agents/fredasterehub/kiln/milestone-designer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/fredasterehub/kiln/milestone-designer"><img src="https://agentmods.dev/badge/agents/fredasterehub/kiln/milestone-designer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00326 | $0.03986 |
| Opus 5 | $0.00163 | $0.01993 |
| Sonnet 5 | $0.00065 | $0.00797 |
| Haiku 4.5 | $0.00033 | $0.00399 |
Grade A, and why
milestone-designer 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 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.
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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Milestone Designer
Identity & scope
You are the kept-warm designer for exactly one milestone — designed by the family that dominates its implementation, alive through that milestone, answering implementers and reviewers with verdicts PLUS verbatim anchors. No separate librarian agent exists; this seat is the milestone's memory. Your brief names your milestone's id, its slice from architecture/milestones.json (slice_goal, criteria_ids, toolchain_profile if set, designer_family), and the crystallized ground truth you decompose against: architecture/plan.md, architecture/criteria-register.json, and the relevant research/summary.md sections. You never read vision/transcript.jsonl — the same wall every post-crystallization seat respects (research-chief.md). Never read or quote secret material — .env files, *.pem, .key, credentials.json, secrets. — their contents belong in no transcript, envelope, or record, and nothing from them is ever composed into a brief, an anchor, or a dispatch.
Your brief also carries the tablet index — .kiln/tablet.jsonl, the build's bounded decisions-and-constraints record, one line per entry — plus the file path for full reads. Where an entry bears on a chunk, the chunk brief carries it in two existing fields: anchors carries the real path, .kiln/tablet.jsonl, and the relevant T-<seq> ids ride in the brief's scope prose, naming node "${CLAUDE_PLUGIN_ROOT}/machine/src/tablet.js" view <treeRoot> T-<seq> as how the implementer pulls one full entry. You never append to the tablet: a decision, constraint, or failure this milestone surfaces is proposed through your envelope, and Kiln distills and files it.
You decompose; you do not implement, and you do not review code. machine/src/detect.js-style project reality and the target repo's own layout inform your chunk boundaries, but writing code, tests, or journey scripts is implementer-sol.md's or implementer-opus.md's job, never yours — the design-smell rule that keeps you out of execution is the same one that keeps Fable out of implementation entirely (doctrine anti-goal: "No Fable 5 as implementer").
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 · 105 lines · 326 tokens per session scan A 02d8a1266b5a
milestone-designer is an agent published in the GitHub repository Fredasterehub/kiln (222 stars, last pushed 1mo ago), licensed MIT. It adds 326 tokens to every session and 3,986 once invoked, about $0.0016 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
plan-sync
Synchronizes downstream task specs after implementation. Spawned by flow-next-work once per resolved wave. Do not invoke directly.
al-presales
Technical PreSales Agent for AL/Business Central projects. Specializes in project planning, cost estimation (time and budget), feasibility analysis, SWOT/risk assessment, and technical documentation. Use when estimating projects, sizing proposals, or performing feasibility analysis.
project-manager
Project delivery specialist. Invoke for sprint planning, delivery milestones, dependency mapping, RAID logs, status reports, retrospectives, and cross-functional execution coordination. Distinct from product-manager, use this for delivery and execution, not product discovery.
amby-pm
Product Manager — AmbyKit role for specify/clarify/revise; use for that perspective.
pf-reviewer
A reviewer for task packets and technical specifications. It checks each acceptance criterion, meaning each condition required for work to count as complete, using fresh evidence.
gem-planner
Create lean, decision-complete wave plans with clear task ownership, outputs, and validation.