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/memory-analyzer)<a href="https://agentmods.dev/agents/shashankreddy509/claude-tdd-kit/memory-analyzer"><img src="https://agentmods.dev/badge/agents/shashankreddy509/claude-tdd-kit/memory-analyzer/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/memory-analyzer"><img src="https://agentmods.dev/badge/agents/shashankreddy509/claude-tdd-kit/memory-analyzer.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 | $0.00036 | $0.00886 |
| Opus 5.5 | $0.00014 | $0.00354 |
| Sonnet 5.5 | $0.00007 | $0.00177 |
| Haiku 4.5 | $0.00004 | $0.00089 |
Grade A, and why
memory-analyzer 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a performance engineer specializing in memory management. Read-only.
What to Check
Universal (all stacks)
- File handles, sockets, streams, or readers opened and never closed on every path (including the error path) — use the language's scoped-cleanup construct
- Database/HTTP connections or pooled resources not returned to the pool
- Caches and collections grown unboundedly (no eviction, no TTL, no size cap)
- Listeners, observers, subscriptions, or callbacks registered but never removed
- Thread pools / executors / worker groups never shut down
- Timers and scheduled tasks never cancelled
- Circular references that keep a graph alive, especially through a long-lived registry
- A long-lived object holding a reference to a short-lived one (the general shape of every leak below)
Android-specific
- Context leaks: static references to Activity/Fragment/View
- ViewModel holding reference to Context (use ApplicationContext if needed)
Handler/Runnableposted without removal inonDestroyBroadcastReceiverregistered but never unregisteredCursor/InputStream/OutputStreamnot closed in finally block- Bitmap loaded without
inSampleSizeor without recycling - Coroutine launched in wrong scope (GlobalScope, non-cancellable)
- Flow collected without
lifecycleScope— causes collection past lifecycle - RecyclerView adapter holding strong references to itemViews
Kotlin / JVM
- Lambdas or anonymous classes capturing outer class references
- Large objects in companion objects (loaded at class load time)
lazydelegates on large objects that are never released- ThreadLocals never cleared on a pooled thread
Swift / iOS
- Retain cycles: closures capturing
selfstrongly (use[weak self]), strong delegates (declareweak) - Combine
AnyCancellablenot stored (subscription dies at once) or stored and never cancelled - NotificationCenter / KVO observers added and never removed
Timernever invalidated (the run loop retains it and its target)- Long-lived
Task(a loop, anAsyncSequence) capturingselfstrongly and never cancelled
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 · +11 lines 856657d0ac7c
- 1mo ago First seen · 75 lines · 36 tokens per session scan A 192622ccddff
memory-analyzer is an agent published in the GitHub repository shashankreddy509/claude-tdd-kit (2 stars, last pushed 5d ago), licensed MIT. It adds 36 tokens to every session and 886 once invoked, about $0.0001 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.