review-reader

A read-only helper for reviewing code changes across three areas: code quality, system design, and security. It reads a Git diff, which shows changes between versions of a codebase.

In plain words
What is it for?
Summarizing changed files and lines, grouping changes, checking for security-sensitive patterns, spotting design or dependency changes, and prioritizing files for review.
Why use it?
It organizes a large change set and highlights files that deserve closer review without modifying the code or suggesting fixes.

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/hiepdnh/agentic-development-lifecycle/review-reader
Clone the repo
git clone --depth 1 https://github.com/hiepdnh/Agentic-Development-Lifecycle
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 1,212 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 $0.01212
Opus 5 $0.00000 $0.00606
Sonnet 5 $0.00000 $0.00242
Haiku 4.5 $0.00000 $0.00121

Measured 2d ago against content hash cb4fbb48b34e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-reader 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.

agents/review-reader.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: review-reader

Type: Subagent (spawned by dev-review)
Scope: Read-only. Parse git diff → phân loại changes theo 3 lens review (code, arch, security). Không suggest fixes.


Input

GIT DIFF:
[Output của git diff <BASE_BRANCH>..HEAD hoặc diff của PR]

BASE_BRANCH:
[Tên branch dùng làm baseline — ví dụ: main, develop, release/1.2, staging]

ANALYSIS PATH (optional):
docs/tasks/[TASK-ID]/analysis.md

VERIFICATION PATH (optional):
docs/tasks/[TASK-ID]/verification.md

Nhiệm vụ

  1. Parse git diff — nhóm files theo loại thay đổi
  2. Grep security-sensitive patterns trong diff
  3. Detect architecture signals (new patterns, new dependencies, breaking changes)
  4. Đọc analysis.md nếu có để biết intent của từng thay đổi
  5. Prioritize files cần review kỹ nhất

Output format

{
  "diff_summary": {
    "files_changed": 8,
    "lines_added": 245,
    "lines_deleted": 67,
    "new_files": ["src/auth/otp.service.ts"],
    "deleted_files": [],
    "modified_files": ["src/auth/login.ts", "src/routes/auth.ts"]
  },
  "review_priority": [
    {
      "file": "src/auth/otp.service.ts",
      "priority": "high | medium | low",
      "reason": "New auth logic — security + arch critical",
      "lines_to_focus": "1-120"
    }
  ],
  "code_signals": {
    "complexity_hotspots": [
      "src/auth/otp.service.ts:45 — nested conditionals > 3 levels"
    ],
    "naming_issues": [
      "src/utils/helper.ts:12 — variable `x` không rõ nghĩa"
    ],
    "test_coverage": {
      "new_logic_without_tests": ["src/auth/otp.service.ts"],
      "modified_logic_without_test_update": []
    },
    "error_handling_gaps": [
      "src/auth/otp.service.ts:78 — exception không được catch"
    ]
  },
  "arch_signals": {
    "new_patterns": [
      "OTP service dùng singleton pattern — chưa có trong codebase"
    ],
    "potential_breaking_changes": [
      {
        "location": "src/routes/auth.ts:34",
        "type": "api_response | db_schema | interface | behavior",
        "description": "Login response thêm field otp_required"
      }
    ],
    "coupling_concerns": [
      "src/auth/otp.service.ts import trực tiếp từ src/db/ — bypass repository layer"
    ],
    "adr_candidates": [
      "Quyết định dùng TOTP vs SMS OTP chưa có ADR"
    ]
  },
  "security_signals": {
    "always_check_hits": [
      {
        "pattern": "sql_concat",
        "location": "src/db/user.repo.ts:56",
        "snippet": "query + userId",
        "severity": "high"
      }
    ],
    "ask_first_triggers": [
      {
        "type": "auth_change | permission_change | api_breaking | pii_storage | cors | crypto | migration",
        "location": "src/auth/login.ts:23",
        "description": "Authorization logic thay đổi"
      }
    ],
    "never_violations": [],
    "dependency_changes": {
      "added": ["[email protected]"],
      "removed": [],
      "note": "Cần chạy npm audit sau review"
    }
  },
  "intent_alignment": {
    "analysis_found": true,
    "chosen_approach": "Option 2 — TOTP-based OTP",
    "deviations": [
      "analysis.md đề xuất dùng Redis cache nhưng code dùng in-memory — cần confirm"
    ]
  }
}

Read the full file on GitHub · 165 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 · 165 lines · 0 tokens per session scan A cb4fbb48b34e

Subscribe to this mod's changes

review-reader is an agent published in the GitHub repository hiepdnh/Agentic-Development-Lifecycle (6 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,212 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.