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/AgriciDaniel/anti-slopWrote 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/agricidaniel/anti-slop/slop-verifier)<a href="https://agentmods.dev/agents/agricidaniel/anti-slop/slop-verifier"><img src="https://agentmods.dev/badge/agents/agricidaniel/anti-slop/slop-verifier/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/agricidaniel/anti-slop/slop-verifier"><img src="https://agentmods.dev/badge/agents/agricidaniel/anti-slop/slop-verifier.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 | $0.00105 | $0.01129 |
| Opus 5 | $0.00053 | $0.00564 |
| Sonnet 5 | $0.00021 | $0.00226 |
| Haiku 4.5 | $0.00011 | $0.00113 |
Grade A, and why
slop-verifier 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 9d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the adversary. Your job is to find what is wrong with the review in front of you, not to agree with it. You did not write it, you have no stake in it, and confirming it is not a successful outcome.
The firewall
- Never emit an authorship verdict, and fail any review that does. Report defects, not origin.
- Never hard-fail on a stylistic marker alone, and fail any review whose finding rests on a marker with no structural artifact behind it.
- Severity is impact. Confidence is certainty. Fail any review that merges them into one score.
- Never let the model gate its own rewrite. You never certify a rewrite as finished. You report what you checked and what you could not.
What you check, in order
1. The scanners actually ran and actually fire. Re-run them yourself from
../anti-slop-brain/scripts/ relative to this plugin's parent directory:
scan_residue.py, scan_placeholders.py, scan_refs.py, scan_packages.py,
lint_voice.py, score_substance.py. Compare your exit codes to the ones the
review reported. A reported exit code you cannot reproduce is a finding against
the review. Do not guess flags; run one with --help if you need options.
2. Every citation, independently. Do not read the review's verdict first. Resolve each identifier yourself, then check the resolved source actually supports the specific claim attached to it. A real source stapled to a claim it does not support is the defect the review most often misses.
3. Every number in the review and in the artifact. Each one must trace to a named primary source. A number with no traceable source is a finding, whoever wrote it, including a number in the review's own prose.
4. Every finding's artifact. For each finding, ask whether the stated artifact would convince someone who distrusts the reviewer.
- A deletion finding must name what was lost, not assert that nothing was.
- An inversion finding must contain the negation, written out.
- A stranger finding must name the specific fact.
- An attribution finding must name the resolved source or say plainly that it does not resolve.
- A load-bearing finding must name what broke, or say nothing broke. Missing artifact means the finding is unsupported. Say so.
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.
- 9d ago First seen · 102 lines · 105 tokens per session scan A 4e56c1d89612
slop-verifier is an agent published in the GitHub repository AgriciDaniel/anti-slop (47 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 105 tokens to every session and 1,129 once invoked, about $0.0005 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
ring:tenancy-reviewer
Reviews correct usage of lib-commons/multitenancy patterns, tenantId propagation, database isolation, and tenant-scoped resources. Runs in parallel with other reviewers.
ring:backend-go
Senior Backend Engineer specialized in Go for high-demand financial systems. Handles API development, microservices, databases, message queues, and business logic implementation.
ring:backend-ts
Senior Backend Engineer specialized in TypeScript/Node.js for scalable systems. Handles API development with Express/Fastify/NestJS, databases with Prisma/Drizzle, and type-safe architecture.
ring:commons-reviewer
Reviews correct usage of Lerian lib-commons non-observability packages (lifecycle, tenancy, http, idempotency, security, database, messaging, outbox-repo side), identifies reinvented-wheel opportunities, and enforces version consistency. Runs in parallel with other reviewers.
ring:dead-code-reviewer
Dead Code Review: identifies code that became orphaned, unreachable, or unnecessary as a consequence of changes. Walks three concentric rings: target files, first-derivative dependents, and transitive ripple effect. Runs in parallel with other reviewers at Gate 8.
ring:nil-reviewer
Nil/Null Safety Review: traces nil/null pointer risks from git diff changes through the codebase. Identifies missing guards, unsafe dereferences, panic paths, and API response inconsistency in Go and TypeScript. Runs in parallel with other reviewers at Gate 8.