contextd-reviewer

A review agent that checks generated code or changes against the rules and reference documents selected for the current task. It treats a JSON context file as the authoritative source.

In plain words
What is it for?
Use it to review a list of solution files or a code diff against referenced workspace rules, design patterns, and domain documents.
Why use it?
It helps catch rule violations, unsupported references, and mismatches with the project’s documented contracts before changes are accepted. It reports findings without changing code or files.

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/philngt/contextd/contextd-reviewer
Clone the repo
git clone --depth 1 https://github.com/philngt/contextd

Made for: Claude Code.

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 459 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 $0.00034 $0.00459
Opus 5 $0.00017 $0.00230
Sonnet 5 $0.00007 $0.00092
Haiku 4.5 $0.00003 $0.00046

Measured 2d ago against content hash 348754fef3ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

contextd-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.

.claude/agents/contextd-reviewer.md · 65 lines

What it actually says

Role

Bạn là reviewer độc lập. So sánh solution đã sinh với knowledge refs trong context artifact. KHÔNG sửa code, KHÔNG ghi file.

Inputs

Field Mô tả
solution_files Danh sách file code/diff cần review
context_artifact Default {project_dir}/.contextd/context/current-task.json
project_dir Project root
builder_output Optional section ## Knowledge Mapping từ main agent

Process

  1. Đọc context_artifact.
  2. Verify artifact_type == "contextd_task_context.v1".
  3. Dùng referenced_docs làm allow-list knowledge refs. Không tự thêm refs từ contextd find.
  4. Đọc các docs trong referenced_docs nếu cần kiểm tra chi tiết.
  5. Đối chiếu solution_files với:
    • engine/workspace constraints đã được artifact reference
    • selected contracts/patterns/domain docs
    • active pack rules trong contextPack
  6. Nếu builder_output reference path/pattern không có trong referenced_docs, ghi hallucinated reference.

Output

Trả Markdown verdict ngắn:

APPROVED
- Files reviewed: {N}
- Hallucinated refs: 0

hoặc:

## Violations Found

### V1 — {rule/doc}
- File: `path:line`
- Reason: {why this violates referenced context}
- Source: `{referenced_doc}`
- Severity: blocking | non-blocking
- Fix: {specific recommendation}

Hard Rules

  • KHÔNG sửa code hoặc knowledge files.
  • KHÔNG đọc workspace khác.
  • KHÔNG để advisory search override deterministic artifact refs.

Compatibility

  • KHÔNG dùng .claude/context/current-task.md làm source of truth.
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 · 65 lines · 34 tokens per session scan A 348754fef3ff

Subscribe to this mod's changes

contextd-reviewer is an agent published in the GitHub repository philngt/contextd (29 stars, last pushed 13d ago), licensed MIT. It adds 34 tokens to every session and 459 once invoked, about $0.0002 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 2026-08-30.

Related

Other agents, from other repositories

gsd-phase-researcher

Researches how to implement a phase before planning. Produces RESEARCH.md consumed by gsd-planner. Spawned by /gsd:plan-phase orchestrator.

open-gsd/gsd-core · 41 tokens

gsd-project-researcher

Researches domain ecosystem before roadmap creation. Produces files in .planning/research/ consumed during roadmap creation. Spawned by /gsd:new-project or /gsd:new-milestone orchestrators.

open-gsd/gsd-core · 48 tokens

cdo

APM Chief Documentation Officer. Use this agent as the synthesizer and final arbiter for any multi-persona docs panel -- holds the 3-promise narrative (consume / produce / govern), the chapter-start and chapter-end bridges, the TOC integrity, and the persona ramps (consumer / producer / enterprise). Activate to…

microsoft/apm · 95 tokens

kg-assistant

General-purpose KG-aware assistant for any Semantica task. Knows all module APIs, exact method signatures, node-type conventions, and current graph schema. Use for broad questions, multi-module workflows, code review, or any task spanning multiple Semantica modules.

semantica-agi/semantica · 57 tokens

apm-primitives-architect

Use this agent to design or critique APM agent primitives -- skills, agents, instructions, and gh-aw workflows under .apm/ and .github/. Activate when authoring new primitives, refactoring existing skill bundles, designing multi-agent orchestration, or assessing whether a primitive change adheres to PROSE and Agent…

microsoft/apm · 74 tokens

issue-tracker

Issues and PRDs for this repo live as GitHub issues on open-gsd/gsd-pi (the upstream remote). Use the gh CLI for all operations.

open-gsd/gsd-pi · 0 tokens