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/faridrashidi/cnsplots/agents-mdgit clone --depth 1 https://github.com/faridrashidi/cnsplotsWrote 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/faridrashidi/cnsplots/agents-md)<a href="https://agentmods.dev/instructions/faridrashidi/cnsplots/agents-md"><img src="https://agentmods.dev/badge/instructions/faridrashidi/cnsplots/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 | $0.01376 | $0.01376 |
| Opus 5 | $0.00688 | $0.00688 |
| Sonnet 5 | $0.00275 | $0.00275 |
| Haiku 4.5 | $0.00138 | $0.00138 |
Grade A, and why
cnsplots 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 5d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Use this file as the repo-specific operating manual for branch, validation, commit, and pull request behavior. When two rules appear to overlap, follow the more specific rule.
Working branch rules
- Never work directly on
main. - If starting new work, create and switch to a new branch from
mainnamed<type>/<short-name>such asfeature/<short-name>,bugfix/<short-name>,docs/<short-name>,refactor/<short-name>, orchore/<short-name>. - If you discover local changes while on
main, create the new branch first and continue the work there. - If already on the intended work branch, continue there unless explicitly told to create a new branch.
- Do not rename or delete branches unless explicitly asked.
- Do not use
ghto create branches; usegit.
Implementation rules
- Follow the smallest-change approach that fully solves the task.
- Keep the diff scoped to the task at hand. If you notice a separate issue, mention it instead of bundling it into the same change.
- Do not make unrelated refactors or opportunistic cleanup unless explicitly asked.
- Ask before:
- adding or removing dependencies
- changing CI, build, release, or deployment files
- modifying infrastructure, secrets, or environment configuration
- running destructive commands
Validation rules
- Before opening a pull request, run:
make testmake lint
- Run validation after the proposed changes are in place so the results match the branch you plan to submit.
- If either command fails:
- fix the issue when it is clearly in scope
- otherwise stop and report the failure clearly, including which command failed
- Do not claim tests passed unless they were actually run successfully.
Commit rules
- Keep commits small and messages clear.
- Prefer a single commit for a small, self-contained change.
- For larger work, use multiple logical commits rather than one large commit.
- Do not amend, squash, or rewrite existing commits unless explicitly asked.
- Each commit message must start with
<emoji> <subject>. - Use a Unicode Gitmoji, not a shortcode.
- In the subject line, do not add a scope, colon, or trailing period.
- Base the subject only on the staged diff.
- Do not infer intent from unstaged files, branch names, task titles, or unrelated context.
- Prefer the smallest accurate claim.
- When multiple edits exist, describe only the dominant change.
- Write in imperative mood.
- Capitalize the first word unless syntax or style requires otherwise.
- For subject use at most five words, excluding the emoji.
- Add a body only when it meaningfully explains why, highlights follow-up work, or calls out a breaking change.
- If you add a body, leave one blank line after the subject and keep the body concise.
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.
- 5d ago First seen · 139 lines · 1,376 tokens per session scan A 88d560e79c55
cnsplots AGENTS.md is an instructions file published in the GitHub repository faridrashidi/cnsplots (661 stars, last pushed 3d ago), licensed BSD-3-Clause. It adds 1,376 tokens to every session, about $0.0069 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
marimo AGENTS.md
AGENTS.md instructions for marimo-team/marimo, covering marimo development guidelines, your primary responsibility is to the project and its users, quick setup, development commands and python.
streamlit copilot-instructions.md
Copilot instructions for streamlit/streamlit, covering streamlit repo overview, tech stack, folder structure, shell & build policy and make commands.
marimo copilot-instructions.md
Copilot instructions for marimo-team/marimo: For example, if there is a frontend change to make a border thicker, how does this look in run mode, app-view and edit-view? For a backend change, has the user tested different scenarios?
streamlit python_tests.instructions.md
Instructions for streamlit/streamlit, covering python unit test guide, key principles, running tests and typing tests.
streamlit agents.instructions.md
Instructions for streamlit/streamlit, covering agent definitions, file format, best practices, cross-platform compatibility and slash command support.
streamlit protobuf.instructions.md
Instructions for streamlit/streamlit, covering protobuf, compile protobuf and important files.