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/ueberdosis/tiptap/prgit clone --depth 1 https://github.com/ueberdosis/tiptapWhat 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 | $0.00262 | $0.00262 |
| Opus 5 | $0.00131 | $0.00131 |
| Sonnet 5 | $0.00052 | $0.00052 |
| Haiku 4.5 | $0.00026 | $0.00026 |
Grade A, and why
PR 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 2d 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
When asked to write a pull request description, use the following template:
## Changes Overview
<!-- Briefly describe your changes. -->
## Implementation Approach
<!-- Describe your approach to implementing these changes. Keep it concise. -->
## Testing Done
<!-- Explain how you tested these changes. Link to test scenarios or specs if relevant. -->
## Verification Steps
<!-- Describe steps reviewers can take to verify the functionality of your changes. -->
## Additional Notes
<!-- Add any other notes or screenshots about the PR here. -->
## Checklist
- [ ] I have created a [changeset](https://github.com/changesets/changesets) for this PR if necessary.
- [ ] My changes do not break the library.
- [ ] I have added tests where applicable.
- [ ] I have followed the project guidelines.
- [ ] I have fixed any lint issues.
## Related Issues
<!-- Link any related issues here -->
When generating the pull request description, ensure it is clear, concise, and follows the provided template. Focus on the key aspects of the changes made, how they were implemented, and how they can be verified.
Make it as minimal as possible to convey the necessary information effectively without causing to much noise and making it hard to read.
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.
- 2d ago First seen · 44 lines · 262 tokens per session scan A df3640ce874e
PR is an instructions file published in the GitHub repository ueberdosis/tiptap (38,197 stars, last pushed 5d ago), licensed MIT. It adds 262 tokens to every session, about $0.0013 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
vscode committing.instructions.md
Guidelines for creating git commits — respecting signing configuration, verification hooks, and referencing GitHub issues.
uview-plus AGENTS.md
AGENTS.md instructions for ijry/uview-plus, covering agents, 提交规范, 发布规范 and uview-plus说明.
nimbalyst CLAUDE.md
Claude Code instructions for nimbalyst/nimbalyst, covering claude.md, critical rules (read first), keep commit messages and changelog entries short, write and run tests for behavioral changes and no dynamic imports in electron main process.
vscode source-code-organization.instructions.md
VS Code source code organization — layers, target environments, dependency injection, and folder structure conventions. Reference when adding new modules, services, or contributions.
daisyui code_generation_with_git.instructions.md
Instructions for saadeghi/daisyui, covering activation, initial setup, development loop, error handling and session end.
planning-with-files AGENTS.md
AGENTS.md instructions for OthmanAdi/planning-with-files, covering agents.md — planning-with-files agent reference card, commit rules, release checklist (12 steps), version bump scope and changelog format.