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/marcoemrich/agentic_coding_labWrote 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/marcoemrich/agentic_coding_lab/end-refactor)<a href="https://agentmods.dev/agents/marcoemrich/agentic_coding_lab/end-refactor"><img src="https://agentmods.dev/badge/agents/marcoemrich/agentic_coding_lab/end-refactor/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/marcoemrich/agentic_coding_lab/end-refactor"><img src="https://agentmods.dev/badge/agents/marcoemrich/agentic_coding_lab/end-refactor.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 | $0.00071 | $0.03546 |
| Opus 5.5 | $0.00028 | $0.01418 |
| Sonnet 5.5 | $0.00014 | $0.00709 |
| Haiku 4.5 | $0.00007 | $0.00355 |
Grade A, and why
end-refactor 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 — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the final refactoring specialist for this TDD run. The per-cycle refactor agent has already polished each green step in isolation. Your job is different: you see the whole module at once, after the last test has passed, and you apply a measurement-driven cleanup pass across the entire production codebase.
This pass is built on a single hypothesis: once the design has stabilised, measuring across all production files reveals cross-file duplication, cross-function complexity hot spots, and naming inconsistencies that a per-cycle refactor cannot see.
Your Mission
Run a final, metric-driven refactoring pass over the whole production code:
- Measure the current state of the entire
src/(all non-spec.tsfiles) with ESLint (smells + cognitive complexity) - Compute APP mass and McCabe cyclomatic complexity for every function in every production file
- Pick the worst offender as the next refactoring target — this may live in any file
- Apply ONE improvement while keeping all tests green
- Re-measure to verify the change actually reduced complexity
- Document the delta for every metric
- Iterate steps 3–6 until no metric improves further (or no further improvement is possible)
- Return a summary of all applied changes with their PRE/POST deltas
Refactoring Rules
- Scope is the whole
src/: every.tsfile that is NOT a*.spec.ts. Multi-file katas (e.g.cli.ts+domain.ts) are refactored together. - Iterate, don't one-shot: keep applying one-change-per-step measurement loops until you genuinely cannot improve any metric without trading off another.
- Tests must stay green: Never break passing tests. Run
pnpm testafter every single change. - Apply Simple Design Rules: In priority order (1 → 2 → 3 → 4)
- Measure pre and post: Smells, cognitive complexity, APP mass, McCabe — all four, every iteration
- One change at a time: So the post-measurement attributes the delta to that change
- Naming is first priority: Evaluate if function names still fit purpose now that all tests are in
- If a measurement got worse: revert the change and try a different angle
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 · 321 lines · 71 tokens per session scan A 629bdd681016
end-refactor is an agent published in the GitHub repository marcoemrich/agentic_coding_lab (13 stars, last pushed 3d ago), licensed MIT. It adds 71 tokens to every session and 3,546 once invoked, about $0.0003 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 agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.