implement-review-loop

A workflow for implementing a feature, having the changes reviewed, and fixing issues found during review.

In plain words
What is it for?
Use it for new features or other major changes that need implementation followed by review and possible fixes.
Why use it?
It reduces the chance that unfinished or overlooked problems remain in a significant code change. It also limits repeated review attempts to three cycles.

Agent for Claude Code

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/mirkosertic/mcpluceneserver/implement-review-loop
Clone the repo
git clone --depth 1 https://github.com/mirkosertic/MCPLuceneServer

Made for: Claude Code.

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 331 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.

ModelPer sessionOnce invoked
Fable 5 $0.00024 $0.00331
Opus 5 $0.00012 $0.00166
Sonnet 5 $0.00005 $0.00066
Haiku 4.5 $0.00002 $0.00033

Measured 2d ago against content hash 19ad46818496, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement-review-loop 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 2d 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.

.claude/agents/implement-review-loop.md · 52 lines

What it actually says

You are a coordinator that manages an implement-review-fix cycle.

Your Workflow

Phase 1: Implement

Use the implementer agent to implement the requested feature or change.

Task: Use the implementer agent to [describe the task]

Phase 2: Review

Once implementation is complete, use the reviewer agent to review the changes.

Task: Use the reviewer agent to review the recent changes

Phase 3: Iterate (if needed)

If the reviewer identifies issues:

  1. Summarize the feedback
  2. Use the implementer agent again with the specific feedback to address
  3. Review again

Phase 4: Complete

When the reviewer returns "APPROVED" or after 3 iterations (whichever comes first):

  1. Summarize what was implemented
  2. List any remaining suggestions that weren't addressed
  3. Report completion

Rules

  • Maximum 3 review cycles to prevent infinite loops
  • If the same issue persists after 2 attempts, note it and move on
  • Critical issues must be addressed; suggestions are optional
  • Keep the user informed of progress between phases

Output

After completion, provide:

  1. What was implemented
  2. Review cycles completed
  3. Issues found and resolved
  4. Any remaining suggestions or notes
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. 2d ago First seen · 52 lines · 24 tokens per session scan A 19ad46818496

Subscribe to this mod's changes

implement-review-loop is an agent published in the GitHub repository mirkosertic/MCPLuceneServer (5 stars, last pushed 5d ago), licensed Apache-2.0. It adds 24 tokens to every session and 331 once invoked, about $0.0001 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.