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/lluvr/frame-check/agents-mdgit clone --depth 1 https://github.com/lluvr/frame-checkWrote 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/lluvr/frame-check/agents-md)<a href="https://agentmods.dev/instructions/lluvr/frame-check/agents-md"><img src="https://agentmods.dev/badge/instructions/lluvr/frame-check/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 | $0.01538 | $0.01538 |
| Opus 5 | $0.00769 | $0.00769 |
| Sonnet 5 | $0.00308 | $0.00308 |
| Haiku 4.5 | $0.00154 | $0.00154 |
Grade A, and why
frame-check 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 4d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents (Claude Code, Cursor, Codex, Aider, and similar) working in this repository.
This file is loaded by most agent runtimes the same way CLAUDE.md
or .cursorrules is. Read it before making changes.
What this repo is
lluvr/frame-check is the public canonical repository for the
Frame Check MCP server: a structural framing analysis tool
distributed as the PyPI package frame-check-mcp. The MCP server
gives any MCP-compatible AI client (Claude Desktop, Cursor, Cline,
Continue.dev, etc.) deterministic structural framing analysis as a
tool, with $0.00 per query at the server (no LLM calls server-side;
optional caller-side LLM judgment for V4.2 capability).
The repository ships the source the wheel is built from, the adopter-facing documentation, the calibration corpus, the worked examples, and the validation harness scaffold.
What goes in this repo
This repository ships only what an adopter needs to install, run, extend, and verify Frame Check. The scope is fixed:
- Python source at the repo root (
mcp_server.py,framing.py,comparison.py,frame_library.py, etc.) and theframecheck_mcp/package wrapper. - Tests under
tests/. - Build + lift infrastructure under
scripts/(canon_audit.sh,lift_dry_run.py,mcp_conformance_driver.py,_release_lib/). - Adopter-facing documentation:
README.md,CONTRIBUTING.md,GOVERNANCE.md,SECURITY.md,CODE_OF_CONDUCT.md,RELEASING.md,ROADMAP.md,CHANGELOG.md,LICENSE,NOTICE,CITATION.cff,AGENTS.md(this file), and thedocs/tree (MCP_SERVER, COOKBOOK, FRAME_DIVERGENCE_CONTRACT). - The Frame Vocabulary Standard catalog at
data/frame_library/, the worked examples atdata/worked_examples/, the transmissions atdata/transmissions/, and calibration corpora.
Anything outside that scope does not enter the repository. The following content shapes are never committed here, regardless of how relevant they feel to the change in front of you:
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.
- 4d ago First seen · 148 lines · 1,538 tokens per session scan A 917007c0721b
frame-check AGENTS.md is an instructions file published in the GitHub repository lluvr/frame-check (0 stars, last pushed 25d ago), licensed Apache-2.0. It adds 1,538 tokens to every session, about $0.0077 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 2026-08-31.
Other instructions, from other repositories
claude-prompts-mcp CLAUDE.md
Claude Code instructions for minipuft/claude-prompts-mcp, covering claude prompts mcp -- operator handbook, core principles, node.js support boundaries, validation gates (one contract, impact-aware subsets) and fleet standards upstream (minipuft/repository-standards).
claude-prompts-mcp AGENTS.md
AGENTS.md instructions for minipuft/claude-prompts-mcp, covering agent rules · claude prompts mcp, canonical ownership and loading, core principles, node.js support boundaries and validation gates (one contract, impact-aware subsets).
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
powerbi-mcp AGENTS.md
Instructions for sulaiman013/powerbi-mcp, covering power bi mcp server - agent guide, what this server does, golden rules, recommended workflows and prompts (guided workflows).
powerbi-mcp CLAUDE.md
Instructions for sulaiman013/powerbi-mcp, covering claude.md and developer notes.
pubcrawl CLAUDE.md
Claude Code instructions for nickjlamb/pubcrawl, covering claude.md, project overview, commands, testing and architecture.