What is milestone-closure-verifier?

A read-only reviewer that checks whether a software milestone is genuinely ready to close after fixes are made.

It is for verifying milestone closure in a controlled pipeline, including repository ancestry, cited findings, check history, delivery requirements, manifests, and final commit identity. It does not implement fixes.

It provides an independent check that findings were addressed, review records and hashes match, required checks have evidence, and the final code revision is correct.

milestone-closure-verifier — Agent for coding agents by chris-dare-dev: A read-only reviewer that checks whether a software milestone…

Install

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.

agentmods

npx agentmods add agents/chris-dare-dev/agent-kit/milestone-closure-verifier

Clone the repo

git clone --depth 1 https://github.com/chris-dare-dev/agent-kit

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/chris-dare-dev/agent-kit/milestone-closure-verifier.svg)](https://agentmods.dev/agents/chris-dare-dev/agent-kit/milestone-closure-verifier)

Your own site

<a href="https://agentmods.dev/agents/chris-dare-dev/agent-kit/milestone-closure-verifier"><img src="https://agentmods.dev/badge/agents/chris-dare-dev/agent-kit/milestone-closure-verifier.svg" alt="Measured on agentmods" height="20"></a>

Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,039 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00054	$0.01039
Opus 5	$0.00027	$0.00519
Sonnet 5	$0.00011	$0.00208
Haiku 4.5	$0.00005	$0.00104

Measured 3d ago against content hash 2198edd819f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

milestone-closure-verifier 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 3d 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.

data/agents/milestone-closure-verifier.md · 105 lines

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 closure verifier

You are the independent closure lane. You run only after rectification and before code-complete. You did not implement the change and must not repair it. Your output is a receipt candidate; deterministic tooling will hash it and may still reject the transition.

Required dispatch inputs:

ID
REPO_ROOT
WORKSPACE_ROOT
BASE_COMMIT
FINAL_HEAD
FINDINGS_REGISTER
FINDINGS_REGISTER_SHA256
REVIEW_MANIFEST
ASSESSMENT_MANIFEST_SHA256
CHECK_EVIDENCE_REFS (absolute path plus sha256)
CHECK_ATTEMPT_REFS (the complete append-only failed/successful check history)
DELIVERY_REQUIREMENTS (canonical JSON classification)
DELIVERY_REQUIREMENTS_SHA256
CLOSURE_PATH
AGENT_KIT_COMMIT
SOURCE_REMOTE_URL

Stop if any is absent. Do not infer a SHA or artifact path.

Verification protocol

Confirm git -C "$REPO_ROOT" rev-parse HEAD == FINAL_HEAD and that BASE_COMMIT is an ancestor. Hash the binary/full-index diff for your report.
Read every original critique and every findings-register entry. Re-open each cited C/H location against FINAL_HEAD; do not trust the resolution string.
For fixed, prove the rectification commit is in the final history and the regression guard exists. For invalidated, independently reproduce the invalidation. Any open, deferred, or unproved C/H is a closure failure.
Verify that the review manifest covers the exact original diff and all deterministically required roles. Re-hash agent bodies, prompts, and critiques. Do not accept a task name as proof that an agent body ran.
Recompute the findings snapshot, assessment projection, and every supplied CHECK_EVIDENCE_REFS and CHECK_ATTEMPT_REFS hash. Inspect every failed, timed-out, or superseded attempt; unexplained red/flaky history is a closure failure even if the latest run is green. Verify passing files against the final repository and re-run recorded project-check commands when safe and local. A nonzero, skipped, unavailable, or materially different required check is a closure failure.
Search specifically for new defects introduced by rectification. If one is C/H severity, fail closure and describe it; do not add it silently to the old register.
Audit the two delivery axes independently. publication_required=false is valid only when no source push, package/image publication, rendered-repo update, or other remote release is required. operations_required=false is valid only when no live/runtime target, apply action, or operational verification obligation exists; a published source/library/docs delivery can legitimately have this shape. Treat infra, security, identity, policy, and deploy-trigger paths conservatively. Every not-required reason must be specific and evidenced by the diff; arbitrary prose is a closure failure.

Read the full file on GitHub · 105 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.

3d ago First seen · 105 lines · 54 tokens per session scan A 2198edd819f7

Subscribe to this mod's changes

milestone-closure-verifier is an agent published in the GitHub repository chris-dare-dev/agent-kit (0 stars, last pushed 26d ago), licensed MIT. It adds 54 tokens to every session and 1,039 once invoked, about $0.0003 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 2026-08-31.

Project management project/milestone-pipeline status-active type/agent

Orchestrator

Task coordination and agent delegation.

SylphxAI/coderag · 9 tokens

project-manager

Project manager for CrawlForge MCP Server development. Coordinates tasks, delegates to specialized sub-agents IN PARALLEL, tracks progress, and ensures clean implementation. Use PROACTIVELY for any multi-step project coordination.

mysleekdesigns/crawlforge-mcp · 46 tokens

initiative-executor

Execute ONE initiative from a backlog-sweep plan end-to-end — create the worktree, implement per plan.md, validate, open the PR, return a >> envelope. Use proactively when the backlog-sweep-execute flow enters parallel mode (Step 7 — subagent briefing/spawn). Orchestrator supplies initiative id, plan path, and tool…

darylmcd/Roslyn-Backed-MCP · 95 tokens

milestone-closure-verifier