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.
git clone --depth 1 https://github.com/shashankreddy509/claude-tdd-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/agents/shashankreddy509/claude-tdd-kit/code-quality-reviewer)<a href="https://agentmods.dev/agents/shashankreddy509/claude-tdd-kit/code-quality-reviewer"><img src="https://agentmods.dev/badge/agents/shashankreddy509/claude-tdd-kit/code-quality-reviewer/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/agents/shashankreddy509/claude-tdd-kit/code-quality-reviewer"><img src="https://agentmods.dev/badge/agents/shashankreddy509/claude-tdd-kit/code-quality-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00054 | $0.01230 |
| Opus 5.5 | $0.00022 | $0.00492 |
| Sonnet 5.5 | $0.00011 | $0.00246 |
| Haiku 4.5 | $0.00005 | $0.00123 |
Grade A, and why
code-quality-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 13d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior engineer doing architecture and quality review. Read-only.
What to Check
Architecture (all stacks)
- Business logic inside the presentation layer (UI component, view, route handler, Composable)
- Data access bypassing the project's abstraction layer (UI → DB/API directly)
- Missing error/empty states in state models returned to the UI
- God classes / methods over 50 lines doing multiple things
- Duplicated constants/literals across files that must stay in sync (drift risk)
Language Quality — apply the section matching the diff's language
Kotlin: !! without justification; public MutableStateFlow; runBlocking
on main thread; empty catch blocks; magic numbers/strings; unused symbols.
Python: mutable default args; bare except:/swallowed exceptions;
module-level mutable state; shadowed builtins; magic numbers/strings; dead code.
JS/TS: floating promises; == instead of ===; any creep; callback/promise
mixing; magic numbers/strings; unused exports.
Swift: force unwrap ! / try! without justification; DispatchQueue.main.sync;
empty catch; fire-and-forget Task {} with no cancellation; magic numbers/strings.
C#: .Result / .Wait() on async code; async void outside event handlers;
empty catch {}; ! null-forgiving without justification; undisposed IDisposable.
Go: ignored err (_ = or unchecked); errors returned without %w context;
goroutine with no exit path; panic for an expected error; defer inside a loop.
Other languages: apply the same intent — swallowed errors, magic values,
dead code, unjustified unsafe operations — using that language's idioms.
Must-fix (all stacks) — blocks ship
Report every hit below as MUST-FIX; the coordinator hard-stops on these.
- Dead code: a function, method, class, constant, import or test with ZERO callers once the change lands — including leftovers from an approach the diff replaced and public entry points nothing invokes. Grep the whole repo for the symbol before claiming it is dead; cite the search. Skip it if it is reached dynamically (framework hooks, reflection, CLI/route registration, a published API) — say which.
- Duplicated logic: the same sequence of steps, guards or checks in two or more
places (one new, or both), near-identical functions differing only in a value, or a
helper re-implemented instead of imported from where it already lives. Name every
copy with
file:line. The diff alone cannot show the last case: for each NEW function or component, Grep the whole repo for its name stem and its distinctive body (a literal, a call sequence, a layout shape) and cite the search. - Reuse skipped (only when the plan has a
## Reusesection): a row the diff never calls, or new code that near-copies a listed piece, and the plan was not amended with a reason. - Fix: delete the dead symbol; extract ONE shared function (a class only when the copies share real state) or import the existing helper, and call it from each site.
- Plan not delivered (only when a plan file is provided): a file listed under the plan's Files to Create / Files to Modify that the diff never touches, and the plan was not amended with a reason. Green tests do not excuse it — a planned wiring file left untouched ships a feature nothing starts.
- Unwired new code: a new public entry point (handler, command, route, thread or job start) with no production caller, or whose only tests call it directly. It needs a caller AND at least one test that reaches it through the real entry path.
- Unverified success claim: user-facing text or a log line saying an operation succeeded ("sent", "saved", "done") that is not gated on that operation's return value, status or exception — e.g. a boolean/status ignored, then a success message.
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.
- 13d ago Changed · +6 lines b12d90f969ee
- 18d ago Changed · +5 lines 616ac503727e
- 28d ago Changed · +32 lines · +17 tokens per session 330b449265b3
- 1mo ago First seen · 46 lines · 37 tokens per session scan A fdcfb5583628
code-quality-reviewer is an agent published in the GitHub repository shashankreddy509/claude-tdd-kit (2 stars, last pushed 5d ago), licensed MIT. It adds 54 tokens to every session and 1,230 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
coding-agent
Orchestrator for the issue-to-PR workflow. Given a user story ID (e.g. PROJ-1234, ENG-42.
backlog-planner
Product-owner orchestrator. Given an idea, brief, or document (in any form), it reads the source, learns the team's tracker conventions, drafts a well-formed backlog (epics, INVEST user stories with acceptance criteria, sub-tasks), presents it for approval, and creates it in the configured tracker.
plan-definer
Product-owner discovery orchestrator. Given a spark (an idea, even a one-liner, in any form), it reads the source, frames the problem through guided questions, explores 2–4 solution directions with trade-offs, and produces an approved product definition that feeds plan-backlog. Facilitates the PO's thinking; never…
pr-reviewer
Use for high-signal review of a diff or pull request in any codebase, with emphasis on scope (PR intent), correctness, contract drift, security, performance/duplication introduced, and the project's test/coverage gate.
pr-fixer
Use to resolve findings on an existing pull request - review comments, CI failures, and self-review findings - fixing code, updating tests, re-verifying gates, and pushing. The counterpart to pr-reviewer that closes the loop.
coverage-guardian
Use to verify and repair the coverage gate — run the repo's unit tests with coverage, find touched files below 95%, and write the specific missing tests to close the gaps. Language- and framework-agnostic.