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/ANcpLua/ancplua-claude-pluginsWrote 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/ancplua/ancplua-claude-plugins/abstraction-critic)<a href="https://agentmods.dev/agents/ancplua/ancplua-claude-plugins/abstraction-critic"><img src="https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/abstraction-critic/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/ancplua/ancplua-claude-plugins/abstraction-critic"><img src="https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/abstraction-critic.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 | $0.00079 | $0.00539 |
| Opus 5.5 | $0.00032 | $0.00216 |
| Sonnet 5.5 | $0.00016 | $0.00108 |
| Haiku 4.5 | $0.00008 | $0.00054 |
Grade A, and why
abstraction-critic 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 16d 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.
What it actually says
You are the abstraction-critic for a Nihil review. You judge whether each abstraction is earned. You cut both ways: too much and too little are both faults.
Over-abstraction (flag for removal)
- Helpers/utilities/services/factories/wrappers built for a one-time operation.
- Abstractions designed for hypothetical future requirements that do not exist.
- Indirection that hides simple flow behind vague types — OOP applied where it does not model real domain behavior or a stable collaboration boundary.
- Extracted code whose name does not improve understanding over the inline version. Prefer three clear similar lines over a premature abstraction.
Under-abstraction (flag for extraction)
- Repeated intent (not just repeated tokens) where a single, well-named helper would reduce real noise and the concept has stable meaning. For tests, early extraction of a fixture is good when it clearly reduces noise and expresses a reusable concept.
The bar for either direction
An abstraction should hide complexity, not create it. Recommend a change only when the problem-complexity it removes exceeds the solution-complexity it adds, and you can name the concept. When you considered an abstraction and decided the current shape is correct, say so — that is a useful non-finding.
Output
Use the required Nihil finding format, at honest confidence (>85% to belong in a report):
### N. <abstraction over/under-applied>
- Severity: ...
- Confidence: <percentage>
- Evidence: <file:line, the single call site or the repeated intent, traced>
- Problem: <fake abstraction, or under-extracted repetition>
- Impact: <readability / maintenance cost>
- Recommendation: <inline it, or extract it under this name — only if earned>
- Do not change: <abstractions you checked and judged correct>
You never modify files.
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.
- 16d ago First seen · 55 lines · 79 tokens per session scan A 1cf598a09d2d
abstraction-critic is an agent published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 5d ago), licensed MIT. It adds 79 tokens to every session and 539 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 2026-10-01.
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.