Claude Code Development Kit is a starter workflow that gives Claude Code project context, working notes, verification commands, review commands, and hooks for maintaining them across sessions. It is for beginners and intermediate users building applications or side projects who want Claude Code to understand the codebase and check its work. The catalogue entries are the kit's skills and commands.
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.
npx skills add peterkrueck/Claude-Code-Development-Kit --skill review-workgit clone --depth 1 https://github.com/peterkrueck/Claude-Code-Development-KitWrote 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.
[](https://agentmods.dev/skills/peterkrueck/claude-code-development-kit/review-work)<a href="https://agentmods.dev/skills/peterkrueck/claude-code-development-kit/review-work"><img src="https://agentmods.dev/badge/skills/peterkrueck/claude-code-development-kit/review-work/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/peterkrueck/claude-code-development-kit/review-work"><img src="https://agentmods.dev/badge/skills/peterkrueck/claude-code-development-kit/review-work.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 105 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 233 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 272 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00143 | $0.02961 |
| Opus 5.5 | $0.00057 | $0.01184 |
| Sonnet 5.5 | $0.00029 | $0.00592 |
| Haiku 4.5 | $0.00014 | $0.00296 |
Grade A, and why
review-work 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Work — Automated Code Review
Review uncommitted code changes using Claude sub-agents as independent reviewers. The invoking agent (you) triages the diff and decides who reviews; reviewers self-prime via /prime, verify API/library claims via Context7, and report against progress.md intent.
This skill is run by an AI, not by a human — use judgment about the change you just made. Don't apply a fixed rubric mechanically. Zero external dependencies: reviewers are Claude sub-agents.
Process
Step 1: Capture the Diff (+ Tests)
Run these and save the output:
git diff --stat HEAD
git diff HEAD
git diff HEAD captures uncommitted work — the normal pre-commit flow. If the work was already committed (e.g. direct-to-main), review the last commit instead: git diff HEAD~1 HEAD (or git show HEAD).
If the project has a test command configured and relevant source changed, run it and capture the output:
# Use whatever test/build command is appropriate for this project's stack.
# e.g. npm test · pytest · cargo test · go test ./... · the test_command in
# hooks/config/pipeline.json if set.
Test/build failures are the #1 finding for every reviewer — include the failure output in each reviewer's prompt verbatim.
Step 2: Triage
Look at the changed file paths and produce two lists.
Impacted modules — by default the whole project is one scope (one project per repo). Only split into modules/components when the diff clearly spans distinct top-level areas (e.g. api/ vs web/, backend/ vs frontend/). If it's all one area, that's a single scope — don't manufacture splits.
Risk surfaces — flag the presence of any of these generic surfaces. For each one that fires, inject the matching focus-area line into reviewer prompts in Step 4:
| Surface | Inject this focus-area line |
|---|---|
| Authentication / authorization | "Auth code touched — check for privilege escalation, missing access checks, and tokens/sessions handled correctly." |
| Database / schema migration | "Schema migration touched — check locking, backfills, NOT NULL on existing rows, and that access rules/constraints are preserved." |
| Configuration / secrets | "Config or secrets touched — confirm no secrets are hardcoded or logged, and environment-specific values aren't baked into source." |
| Dependency manifest | "Dependency manifest changed — confirm new deps are pinned, sourced legitimately, and not duplicating existing functionality." |
| Critical-path / user-facing flow | "Critical-path or user-facing flow touched — check error handling, input validation at boundaries, and that the happy path plus failure modes are covered." |
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.
- 1mo ago First seen · 280 lines · 143 tokens per session scan A c0a122dd0f1e
review-work is a skill published in the GitHub repository peterkrueck/Claude-Code-Development-Kit (1,388 stars, last pushed 3mo ago), licensed MIT. It adds 143 tokens to every session and 2,961 once invoked, about $0.0006 per session on Opus 5.5. 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.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…