milestone-reviewer

milestone-reviewer is an agent for Claude Code, Codex from Fredasterehub/kiln. It costs 285 tokens per session (2,249 once invoked), scanned A, original, MIT.

An agent that reviews all the changes and test results belonging to one completed milestone. A milestone is a complete project slice made up of several smaller chunks.

In plain words
What is it for?
Use it to confirm that a milestone's combined changes deliver its stated goal, cover the required criteria, and demonstrate the claimed user journeys.
Why use it?
Reviewing chunks separately can miss problems that appear only when they are combined, such as incomplete coverage or a slice that does not meet its overall goal. This review checks the milestone as a whole and does not make fixes.

Agent for Claude CodeCodex

Written for Claude Code and Codex: effort in frontmatter, but also runs codex exec. Also seen: model in frontmatter; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the kiln plugin — 2 commands, 22 agents shipped together

Good fit Use it to confirm that a milestone's combined changes deliver its stated goal, cover the required criteria, and demonstrate the claimed user journeys.

Compare 6 agents from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add Fredasterehub/kiln
Claude Code
/plugin install kiln

Made for: Claude Code, Codex.

Or install kiln, the plugin that ships this one along with the rest of its 2 commands, 22 agents.

Wrote 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.

agentmods badge for milestone-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/fredasterehub/kiln/milestone-reviewer/github.svg)](https://agentmods.dev/agents/fredasterehub/kiln/milestone-reviewer)
Your own site
<a href="https://agentmods.dev/agents/fredasterehub/kiln/milestone-reviewer"><img src="https://agentmods.dev/badge/agents/fredasterehub/kiln/milestone-reviewer/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.

agentmods 80×15 button for milestone-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/fredasterehub/kiln/milestone-reviewer"><img src="https://agentmods.dev/badge/agents/fredasterehub/kiln/milestone-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 285 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,249 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00285 $0.02249
Opus 5 $0.00143 $0.01125
Sonnet 5 $0.00057 $0.00450
Haiku 4.5 $0.00028 $0.00225

Measured 11d ago against content hash 3acea03b72c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

milestone-reviewer 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 11d 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.

plugins/kiln/agents/milestone-reviewer.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Milestone Reviewer

Identity & scope

You are the milestone_review seat (the routing config's own entry: "cross-family") — the review that closes a whole milestone, distinct from and IN ADDITION TO every chunk's own cross-family review (chunk-reviewer-sonnet.md/chunk-reviewer-sol.md). Chunk review answers "is this one chunk correct and in-contract"; you answer a different question a chunk-scoped read structurally cannot: do this milestone's chunks, taken together, actually deliver the slice_goal architecture/milestones.json named for it? Every chunk can seal on its own and the milestone still fail this one — chunks that are each locally correct but compose into the wrong shape, a slice_goal only partially covered, or a journey suite that demonstrates less than the milestone claims.

You review; you do not fix, and you do not re-review any single chunk's own diff — that already happened. A finding here is about composition, coverage, and slice-level coherence, never a re-litigation of a chunk review already closed with approve.

What you receive

Your brief names the milestone under review: its architecture/milestones.json entry (slice_goal, criteria_ids, designer_family), its spec.md (the chunk decomposition, for what the milestone claims each chunk covers), its chunks.jsonl (every chunk's lifecycle history — you read this directly to confirm every chunk's latest record is genuinely chunk-green before reviewing anything, the same "don't guess, verify" floor every seat in this phase holds), and the target repo's current working-tree/history state. Never read or quote secret material — .env files, *.pem, .key, credentials.json, secrets. — their contents belong in no transcript, envelope, or record; a secret the cumulative diff exposes is named in the security paragraph by location, never by quoting what it holds.

Family routing — read the chunk history, then route yourself

Before reviewing anything, tally chunks.jsonl's chunk-start records for this milestone by implementer_family. Whichever family authored the MAJORITY of this milestone's chunks is the family your review must NOT be — cross-family review only holds its decorrelation guarantee when the reviewing mind differs from the one that dominated implementation, the same law chunk review enforces one level down:

Read the full file on GitHub · 57 lines

Changes

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.

  1. 11d ago First seen · 57 lines · 285 tokens per session scan A 3acea03b72c3

Subscribe to this mod's changes

milestone-reviewer is an agent published in the GitHub repository Fredasterehub/kiln (221 stars, last pushed 1mo ago), licensed MIT. It adds 285 tokens to every session and 2,249 once invoked, about $0.0014 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.

Related

Other agents, from other repositories

style-analyzer

Use this agent after UI implementation or when the user requests design consistency audits. Ensures visual consistency, catches design drift from locked tokens, identifies technical debt in UI code, and guards the integrity of the design language. Context: Multiple UI components were built during the cycle. user…

drobins25/craft · 203 tokens

verifier

Verification agent for /craft:research-verify. Takes a single claim from existing research and attempts to disprove it using independent primary sources. Returns a verdict (CONFIRMED/REFUTED/PARTIALLYTRUE/UNVERIFIABLE) with evidence. NOT a researcher. Does not discover new topics or cast a wide net. Takes one claim…

drobins25/craft · 178 tokens

code-reviewer

Focused code reviewer. Dispatched with a specific lens (security, architecture, or test-coverage). Read-only. Used by /review-team for parallel review.

dwarvesf/dwarves-kit · 36 tokens

party-visionary

Party-mode panelist — the long horizon. Attacks whether the change compounds or makes the next change harder: one-way design commitments, precedent that will be copied, and pairs of things that must be kept in sync forever. Read-only; returns findings as its final message. Seated at tier deep.

chan4lk/specclaw · 0 tokens

frontend-reviewer

Reviews a diff through the FRONTEND lens only (a11y/ARIA, semantic HTML, focus/keyboard, state handling, responsive/viewport, color-only signaling). Read-only. Dispatched by /kit:review-team as the frontend domain lens when the diff touches UI.

dwarvesf/dwarves-kit · 60 tokens

infra-reviewer

Reviews a diff through the INFRA lens only (deploy/rollback safety, CI/CD config, container/IaC least-privilege, secret handling, idempotent provisioning, blast radius). Read-only. Dispatched by /kit:review-team as the infra domain lens when the diff touches deploy or infrastructure.

dwarvesf/dwarves-kit · 67 tokens