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.
npx agentmods add instructions/eric-tramel/slop-guard/agents-mdgit clone --depth 1 https://github.com/eric-tramel/slop-guardWrote 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/instructions/eric-tramel/slop-guard/agents-md)<a href="https://agentmods.dev/instructions/eric-tramel/slop-guard/agents-md"><img src="https://agentmods.dev/badge/instructions/eric-tramel/slop-guard/agents-md.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 | $0.00629 | $0.00629 |
| Opus 5 | $0.00315 | $0.00315 |
| Sonnet 5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
slop-guard AGENTS.md 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 6d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Slop-Guard is a programmatic tool for giving linter-style feedback to an agent on English writing style.
Development
UV
The project uses uv. Always use uv for python command line actions.
uv run ...
uv run --with dependency ...
Make
Run make to see all available targets. Before pushing a PR, run make check to verify formatting, lint, type, and coverage all pass.
Git Workflow
- When asked for a new feature, bug fix, or other code-specific work, check out a new branch on a new git worktree.
Use
ghfor interactions with GitHub. - Create a commit and push a PR with a full description that fills out the following sections.
## Description
[... a paragraph decription of what the PR is ...]
## Why?
[... a paragraph about why this PR needed to exist ...]
## Usage / Demonstration
[... can be as long as necessary, should include code blocks ...]
## Verification
[ ... what was done to verify the PR ... ]
## Issues
[ ... list of Issue items related or that are closed by the PR ... ]
- The PR title should be a simple sentence describing what it is.
- Don't mark PRs as draft when creating them.
- Don't include any AI agent authorship claims (e.g. "[codex]..." or "Authored by: ..." etc.)
Python Style
- Full Google style docstrings for modules, classes, and functions.
- Strong types in 3.11+ python conventions.
- Use TypeAlias to define compositions of types.
- Loud errors, no "defensive" coding.
- Optimized for time-efficient computation, even at the cost of legibility.
- Favor composition over monoliths.
Code Invariants
- No dead code. When a refactor makes something unused, delete it in the same commit. After any API move, grep for all callers — including
benchmark/, tests, and imports — and update them. - MCP return types. Tools must return typed structured payloads (
dict[str, Any]), notstr. Error paths must raiseToolError, not return plain strings. sg-fitrequires contrastive data. Positive-only fitting drives all positive scores to zero. Always require both positives and negatives.- Do not commit
uv.lockchanges unless you explicitly added or removed a dependency —uv rundirties it as a side effect. - Each agent works in its own isolated worktree. If a worktree is shared, never revert or overwrite another agent's uncommitted changes.
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.
- 6d ago First seen · 73 lines · 629 tokens per session scan A da10f64dffac
slop-guard AGENTS.md is an instructions file published in the GitHub repository eric-tramel/slop-guard (163 stars, last pushed 1mo ago), licensed MIT. It adds 629 tokens to every session, about $0.0031 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 instructions, from other repositories
ai-dial-core CLAUDE.md
Claude Code instructions for epam/ai-dial-core, covering claude.md, build & run, set credentials via environment variables, build (skip tests) and run all tests.
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
technocore-chat AGENTS.md
AGENTS.md instructions for flop-labs/technocore-chat: CI runs exactly these — run them before pushing.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).