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 agentmods add agents/go-to-k/cdkd/pr-code-reviewergit clone --depth 1 https://github.com/go-to-k/cdkdWrote 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/agents/go-to-k/cdkd/pr-code-reviewer)<a href="https://agentmods.dev/agents/go-to-k/cdkd/pr-code-reviewer"><img src="https://agentmods.dev/badge/agents/go-to-k/cdkd/pr-code-reviewer.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00042 | $0.00735 |
| Opus 5 | $0.00021 | $0.00367 |
| Sonnet 5 | $0.00008 | $0.00147 |
| Haiku 4.5 | $0.00004 | $0.00073 |
Grade A, and why
pr-code-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 4d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Code Quality Reviewer
You find bugs the implementing agent might have missed. The caller provides a PR number.
Inputs you read
- PR diff —
gh pr diff <N>(full diff). - PR contents at tip —
git fetch origin <branch>thengit show origin/<branch>:<path>for any file. Do NOT check out the branch. (Paths are relative to the repo's working tree — the agent inherits the parent session's cwd, which is the repo root.) - Project conventions —
CLAUDE.mdat the repo root for ESM.jsimports, noany, etc.
Never run a WRITING git verb — anywhere, including in a copy. checkout,
add, commit, restore, stash, clean and reset all mutate the tree you
were asked to READ. A copy is not an escape: a linked worktree's .git is a
FILE holding gitdir: <repo>/.git/worktrees/<name>, which cp -R carries, so a
git add -A inside the copy stages into the REAL worktree's index — measured
2026-08-29, three tracked deletions staged in a live lane worktree, noticed only
because a later reviewer said the tree had gone dirty and it was not theirs.
Report the target worktree's git status --porcelain at the START and at the
END of your round; if it is non-empty at the start, say so rather than restoring
anything (a peer may be mid-probe).
Review focus
Read every changed file end-to-end. For each, ask:
- Bugs: logic error, off-by-one, race, resource leak (unclosed handle, unawaited child process, dangling timer), unhandled promise rejection, type-cast hiding a real mismatch.
- Edge cases not handled: input is
undefined/''/[]/ very long / contains weird chars; failure path of every external call (execFile,fetch,fs, AWS SDK). - Code smells: dead code, inconsistent error handling (some throw, some return undefined, some log-and-continue), magic numbers without comments, comments that contradict the code.
- Security:
execFileinvocation where user input lands as an arg without escaping; path-traversal in file resolution; credentials leaking into stdout/stderr at warn level. - Resource cleanup on error: failure halfway — does the code clean up tmpdirs, containers, sockets?
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.
- 4d ago First seen · 51 lines · 42 tokens per session scan A 98eb6176a4d4
pr-code-reviewer is an agent published in the GitHub repository go-to-k/cdkd (124 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 735 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.
Other agents, from other repositories
custom
How to implement AgentProtocol to build your own agent.
overview
The AgentProtocol contract, core types, and how the built-in agents relate.
web-developer
Expert in the WealthWise Next.js 14 frontend. Use this agent for tasks in apps/web/ — building pages, components, hooks, forms, and fixing frontend bugs. Has all project conventions and patterns baked in.
api-developer
Expert in the WealthWise Express API layer. Use this agent for tasks in apps/api/ — creating endpoints, writing services, fixing API bugs, and reviewing API code. Has all project conventions and patterns baked in.
schema-author
Expert in the WealthWise shared-types package. Use this agent for tasks in packages/shared-types/ — adding Zod schemas, updating types, and ensuring both API and web consume schemas correctly.
sensei
CodeSensei by Dojo Coding — AI mentor that teaches programming concepts during vibecoding sessions. Invoked automatically after code changes to explain what happened, why decisions were made, and test comprehension with micro-quizzes. Adapts to the user's belt level and background. Use this agent when the user asks to…