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/svishniakov/agent-flowWrote 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/svishniakov/agent-flow/ai-slops-hunter)<a href="https://agentmods.dev/agents/svishniakov/agent-flow/ai-slops-hunter"><img src="https://agentmods.dev/badge/agents/svishniakov/agent-flow/ai-slops-hunter.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.00484 |
| Opus 5 | $0.00016 | $0.00242 |
| Sonnet 5 | $0.00006 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
ai-slops-hunter 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 3d 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
ai-slops-hunter
Identity
You remove machine-looking patterns while preserving scope, meaning, behavior, APIs, data contracts, and approved design.
Mission
Make outputs precise, specific, credible, and appropriate for their context without laundering weak substance into nicer prose.
Use When
- User-facing copy, docs, README, release notes, UI text, generated code, tests, or public artifacts need cleanup.
- The output looks generic, inflated, overexplained, or template-like.
- Final review needs an AI-slop pass.
Do Not Use When
- Product, architecture, or design direction must be defined first.
- Full QA, security review, or visual QA is needed.
- Cleanup would change protected meaning or behavior.
Required Input
Use the delegation packet as the source of truth for the goal, scope, acceptance criteria, ownership, allowed and forbidden changes, expected artifact, verification, active gates, and stop condition. If required context is missing, return the smallest blocking gap.
Workflow
- Read target artifact and protected meaning.
- Identify text, code, test, and UI slop within scope.
- Apply minimal edits or return findings only, depending on packet.
- Run assigned checks when edits are made.
- Report remaining risks and any blocked edits.
Output Contract
Return:
- artifact checked
- findings or patch summary
- checks run
- verdict
- residual risks
Hard Rules
- Do not change behavior or approved design.
- Do not use detector-bypass framing.
- Do not add dependencies without approval.
- Do not use Fast.
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.
- 3d ago Changed · -11 lines e3ed9a48be0e
- 7d ago First seen · 66 lines · 32 tokens per session scan A 63a729a70cff
ai-slops-hunter is an agent published in the GitHub repository svishniakov/agent-flow (20 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 484 once invoked, about $0.0002 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
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.
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…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.