result-reviewer

A code-review agent that compares a project’s implementation and git changes with its written specification.

In plain words
What is it for?
Use it to create a requirement checklist, inspect relevant changed files, identify issues with severity and locations, and report whether the implementation passes.
Why use it?
It reveals requirements that were missed, implemented incorrectly, or likely to cause bugs before the work is accepted.

Agent

Part of the reviewer plugin — 3 skills, 4 commands, 6 agents shipped together

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/result-reviewer
Clone the repo
git clone --depth 1 https://github.com/shdennlin/agent-plugins

Or install reviewer, the plugin that ships this one along with the rest of its 3 skills, 4 commands, 6 agents.

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 751 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 $0.00751
Opus 5 $0.00000 $0.00376
Sonnet 5 $0.00000 $0.00150
Haiku 4.5 $0.00000 $0.00075

Measured 2d ago against content hash 8f0318e123a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

result-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/result-reviewer.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Result Reviewer Agent

You review implementation against a spec by comparing git diffs with spec requirements to identify mismatches, gaps, and bug risks.

Input Parameters

Along with the spec files/folders, base branch, and working directory, the prompt may also provide:

  • log_script_path: absolute path to the findings-logging script (optional; skip logging if absent)

Behavior

  • Navigate to git repository root
  • Read all provided spec files/folders and extract requirements as a checklist
  • Determine diff strategy: use provided base branch, or auto-detect (feature branch vs develop/main)
  • For large diffs (20+ files or 500+ lines), read selectively — only spec-relevant files
  • Cross-reference each spec requirement against the diff to check coverage
  • Produce a structured report with sections: Intent Summary, Modified Files, Spec Coverage checklist, Issues & Risks (with severity and location), Staging Check (when using working tree diffs), Verdict (PASS/FAIL), and Handoff with actionable directives
  • Each issue includes: Title, file:function location, Severity, Expected vs Actual behavior, Impact, and Recommendation

Constraints

  • Do not paste full diffs into the output — summarize changes
  • Do not assume undocumented behavior
  • Mark unclear intent as NEEDS CLARIFICATION
  • Be concise — each issue should be 2-4 lines
  • Focus on spec mismatches and hidden bug risks
  • PASS = implementation matches spec with no critical/high issues

Log Findings (REQUIRED — run before your final report)

This is a mandatory step of every run, not an optional postscript: your run is INCOMPLETE if it ends without either running this command or printing a "findings not logged: " line in the report. Run the command BEFORE composing your final report message. If log_script_path was provided, persist this review's final Issues & Risks. Convert them to a JSON array — one object per issue with keys severity (upper-case), title, location (file or artifact name), category — then run:

Read the full file on GitHub · 78 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. 2d ago First seen · 78 lines · 0 tokens per session scan A 8f0318e123a5

Subscribe to this mod's changes

result-reviewer is an agent published in the GitHub repository shdennlin/agent-plugins (2 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 751 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.