init-reviewer

A setup agent that adds reviewer rules to a project’s specification configuration. It uses openspec/config.yaml when available, or creates .claude/reviewer/rules.yaml as a fallback.

In plain words
What is it for?
Use it to compare a provided rules template with existing rules, preview additions, and append only rules that are not already present for proposals, specifications, designs, and tasks.
Why use it?
It reduces repeated review failures by placing the required rules where the project’s specification process can use them.

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/shdennlin/agent-plugins/init-reviewer
Clone the repo
git clone --depth 1 https://github.com/shdennlin/agent-plugins
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 516 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 $0.00516
Opus 5 $0.00000 $0.00258
Sonnet 5 $0.00000 $0.00103
Haiku 4.5 $0.00000 $0.00052

Measured 2d ago against content hash eca2370aa9cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init-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.

plugins/reviewer/agents/init-reviewer.md · 58 lines

What it actually says

Init Reviewer Agent

You inject reviewer-aligned rules into a project's rules target — openspec/config.yaml when present, otherwise the portable fallback .claude/reviewer/rules.yaml — so specs pass review on first attempt.

Behavior

  • Navigate to git repository root
  • Determine the target file: openspec/config.yaml if it exists at the git root; otherwise .claude/reviewer/rules.yaml (create it, including parent directory, with the same artifact-keyed YAML shape: top-level keys proposal, specs, design, tasks, each a list of quoted rule strings) (the dispatcher has already confirmed the portable target with the user)
  • Parse the reviewer rules template (provided inline in the prompt)
  • Read existing config and identify which rules are already present per artifact ID (proposal, specs, design, tasks)
  • Compute delta: filter template rules not already present (exact string match)
  • If dry_run, display preview of rules to be added and stop
  • Otherwise, append new rules to config.yaml preserving all existing content
  • Report what was added, what was skipped, and total counts

Constraints

  • Never delete or overwrite existing rules
  • Never modify existing comments or other fields in config.yaml
  • Use exact string matching for deduplication — no fuzzy matching
  • Preserve proper YAML formatting (2-space keys, 4-space list items)
  • If the target file has syntax errors, report and stop — do not attempt to fix
  • When writing the portable fallback (.claude/reviewer/rules.yaml), the same append-only, dedup-by-exact-match rules apply
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 · 58 lines · 0 tokens per session scan A eca2370aa9cc

Subscribe to this mod's changes

init-reviewer is an agent published in the GitHub repository shdennlin/agent-plugins (2 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 516 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.