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/saadeghi/daisyui/code_generation_with_gitgit clone --depth 1 https://github.com/saadeghi/daisyuiWhat 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 | $0.01006 | $0.01006 |
| Opus 5 | $0.00503 | $0.00503 |
| Sonnet 5 | $0.00201 | $0.00201 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
daisyui code_generation_with_git.instructions.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rules for using Git branches during code generation sessions
Activation
- These rules are ONLY applied when the user explicitly says "#usegit"
- If "#usegit" is not mentioned explicitly with the exact phrase, ignore these rules completely
Initial Setup
- Create a new feature branch with timestamp:
git checkout -b LLM/[$(date +%Y%m%d)]-[TASKNAME]- Replace
[TASKNAME]with a short descriptive name of the task - Example:
git checkout -b LLM/20241005-add-authentication
- Replace
- Confirm branch creation and inform user of the branch name
- Auto-stash any uncommitted changes before starting:
git stash
Development Loop
For each code change iteration, make a to do list for yourself and follow these steps:
- Write/modify code according to the user's requirements according to code generation instructions at .github/instructions/code_generation.instructions.md
- Test the code by writing test files according to testing instructions at .github/instructions/code_generation.instructions.md
- Verify functionality - ensure tests pass and code works as expected
- Stage and commit if tests pass:
git add -Agit commit -m "[descriptive message here]"- Use descriptive commit messages that explain what was added/changed and why
- Report status to user: what was changed, test results, commit hash
Error Handling
- If tests fail, do NOT commit
- Fix the issue and retry the loop
- If multiple attempts fail, ask user for guidance
- If git operations fail, report the error and ask for manual intervention
Session End
- Ask the user for explicit order to merge
#merge [commit message here]. If not received, do not merge. the user must provide a commit message in the mentioned format explicitly. - use the commit message provided by the user in the merge command.
- in the description of the commit message, add the branch name of the feature branch used like "Merged changes from branch [timestamp]" without the
LLM/prefix. - Before merging, show commit history:
git log --oneline - Execute merge:
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.
- yesterday First seen · 100 lines · 1,006 tokens per session scan A 47d39f191f90
daisyui code_generation_with_git.instructions.md is an instructions file published in the GitHub repository saadeghi/daisyui (42,247 stars, last pushed 8d ago), licensed MIT. It adds 1,006 tokens to every session, about $0.0050 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
starwind-ui AGENTS.md
Instructions for starwind-ui/starwind-ui, covering agents.md, project shape, useful commands and contribution conventions.
fundamental-ngx AGENTS.md
Instructions for SAP/fundamental-ngx, covering angular 22+ development guidelines, persona, quick reference, essential commands and build/lint/test specific library.
wonder-blocks storybook.instructions.md
Storybook best practices for Wonder Blocks component stories.
wonder-blocks AGENTS.md
Instructions for Khan/wonder-blocks, covering wonder blocks – agentic workflows & storybook mcp, installing the mcp (consumer setup), storybook mcp server, when it’s available and mcp endpoint.
openbridge-webcomponents watch-radial-instruments.instructions.md
Instructions for Ocean-Industries-Concept-Lab/openbridge-webcomponents, covering watch & radial instruments, architecture overview, key principle: logic in watch.ts, instruments stay thin, shared sibling modules and layering & stacking pattern.
openbridge-webcomponents line-area-charts.instructions.md
Instructions for Ocean-Industries-Concept-Lab/openbridge-webcomponents, covering line/area charts & gauge trend, architecture overview, key principle: logic in base class, subclasses stay thin, base class architecture and line graph (non-filled).