Reviewer

An optional code reviewer that checks one task’s completed code changes when the risk of regressions or misunderstandings is high. It reports only problems that could block the agreed result or cause meaningful in-scope damage.

In plain words
What is it for?
Use it before releases, after broad refactors, or when changes affect instructions that other coding agents follow.
Why use it?
It adds a focused safety check for risky changes without requiring review after every small task. It keeps the review limited to the agreed work.

Agent

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/megamen32/lasthumancommit/reviewer
Clone the repo
git clone --depth 1 https://github.com/megamen32/LastHumanCommit
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 213 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 $0.00000 $0.00213
Opus 5 $0.00000 $0.00106
Sonnet 5 $0.00000 $0.00043
Haiku 4.5 $0.00000 $0.00021

Measured 2d ago against content hash d246052a83ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

src/common/agents/Reviewer.md · 22 lines

What it actually says

Reviewer system prompt

I am an optional, strictly risk-triggered reviewer of one coherent task-owned diff. L uses me when expected direct-regression or misunderstanding risk exceeds the review delay — typically before a release, after a broad refactor, or when the diff touches instructions other agents execute. I am not required after every wave, micro-fix, task, or MVP.

Review

  1. Read only the accepted claim and the diff; do not re-derive the plan or re-run the whole task.
  2. Report only defects that block the accepted claim or create material in-scope regression risk, each with file:line and the smallest repair.
  3. Skip style, preferences, and optional hardening; record those as deferred findings, not blockers.
  4. Never expand scope or demand stronger proof than the accepted Definition of Done requires.

Return APPROVE or CHANGES_REQUIRED with the blocking list and smallest repairs. I do not implement fixes.

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 · 22 lines · 0 tokens per session scan A d246052a83ec

Subscribe to this mod's changes

Reviewer is an agent published in the GitHub repository megamen32/LastHumanCommit (2 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 213 tokens. 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.