dx-impl-review

dx-impl-review is a skill for Claude Code from dikamilo/dx-workflow. It costs 25 tokens per session (1,088 once invoked), scanned A, original, MIT.

A post-implementation check that compares a finished change with its written plan. It reports differences, safety concerns, pattern or standards violations, and other findings in a review file.

In plain words
What is it for?
Use it after a planned change is implemented and its progress checklist is complete. It reviews the code against the plan, project standards, naming glossary, and relevant repository guidance.
Why use it?
It shows whether the delivered work matches what was agreed before implementation. It keeps review separate from fixing, so findings remain visible for the user to decide how to handle.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions subagents.

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 skills/dikamilo/dx-workflow/dx-impl-review
Any agent
npx skills add dikamilo/dx-workflow --skill dx-impl-review
Clone the repo
git clone --depth 1 https://github.com/dikamilo/dx-workflow

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for dx-impl-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/dikamilo/dx-workflow/dx-impl-review.svg)](https://agentmods.dev/skills/dikamilo/dx-workflow/dx-impl-review)
Your own site
<a href="https://agentmods.dev/skills/dikamilo/dx-workflow/dx-impl-review"><img src="https://agentmods.dev/badge/skills/dikamilo/dx-workflow/dx-impl-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,088 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 5.1 $0.00025 $0.01088
Opus 5 $0.00013 $0.00544
Sonnet 5 $0.00005 $0.00218
Haiku 4.5 $0.00003 $0.00109

Measured 5d ago against content hash d112dbc18a51, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

dx-impl-review 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 5d 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.

skills/dx-impl-review/SKILL.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dx-impl-review

The post-implementation gate. Compare what was built against context/changes/<change-id>/plan.md and report — this skill reviews, it never fixes-and-hides the code it is checking. Findings land in a review file and on screen; the user decides what to do.

Guard. Resolve <change-id> under context/changes/. Missing → tell the user to run /dx-new. Under context/archive/ → refuse; an archived change is done. If plan.md's ## Progress still has a - [ ], the change isn't finished — say so and point at /dx-implement <change-id>.

1 — Load

Read plan.md fully (note change.md's type), its Standards to apply checklist and Priors & gotchas, and foundation/glossary.md (a one-line habit — review naming against the project's terms; if the diff's naming clashes with the glossary or reveals a term that only just resolved, invoke dx-domain). Get the diff scope: git log/git diff for the commits that landed this change's phases. Then invoke dx-references with knowledge-layer (how to verify standards compliance), with review-report (the finding-ID/Resolution schema and file convention shared with plan-review and review-triage), and — when type: refactor — also with module-design (depth/seam/deletion vocabulary for the pattern axis).

2 — Review on four dimensions

Fan out to built-in Explore/general-purpose subagents to keep the main context clean — e.g. one for drift, one for safety + standards. Each reads only the files it needs; don't pre-load 20 files here.

  1. Plan-drift — was what's in the diff what plan.md planned? Flag intent mismatches, skipped items, and unplanned scope (extra files/behavior not in the plan). If plan.md carries any of the conditional sections (## Data model, ## API & contracts, ## Failure modes & reversibility), check the diff against what each one planned — a documented undo path or migration that the implementation never shipped is Plan-drift, not a new dimension.
  2. Safety — data loss, destructive/irreversible ops, missing error handling at boundaries, hardcoded secrets, injection.
  3. Patterns — sound structure judged with the module-design vocabulary (deep vs shallow, clean seams, does the interface leak?). Report substantive mismatches with sibling code, not style nits.
  4. Standards compliance — did it follow the plan's matched Standards to apply? Cite the standard for each miss.

Read the full file on GitHub · 44 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. 5d ago First seen · 44 lines · 25 tokens per session scan A d112dbc18a51

Subscribe to this mod's changes

dx-impl-review is a skill published in the GitHub repository dikamilo/dx-workflow (5 stars, last pushed 4d ago), licensed MIT. It adds 25 tokens to every session and 1,088 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

claude-md-improver

Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…

anthropics/claude-plugins-official · 82 tokens

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

gke-workload-security

Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…

google/skills · 181 tokens

gke-reliability

Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).

google/skills · 73 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens