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/haraldbregu/friday/agents-mdgit clone --depth 1 https://github.com/HaraldBregu/fridayWrote 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/haraldbregu/friday/agents-md)<a href="https://agentmods.dev/instructions/haraldbregu/friday/agents-md"><img src="https://agentmods.dev/badge/instructions/haraldbregu/friday/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 | $0.00957 | $0.00957 |
| Opus 5 | $0.00478 | $0.00478 |
| Sonnet 5 | $0.00191 | $0.00191 |
| Haiku 4.5 | $0.00096 | $0.00096 |
Grade A, and why
friday 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.
Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.
1. Think Before Coding
Don't assume. Don't hide confusion. Surface tradeoffs.
Before implementing:
- State your assumptions explicitly. If uncertain, ask.
- If multiple interpretations exist, present them - don't pick silently.
- If a simpler approach exists, say so. Push back when warranted.
- If something is unclear, stop. Name what's confusing. Ask.
2. Simplicity First
Minimum code that solves the problem. Nothing speculative.
- No features beyond what was asked.
- Do not over-engineer the solution; actively look for the simplest solution that satisfies the request.
- No abstractions for single-use code.
- No "flexibility" or "configurability" that wasn't requested.
- No error handling for impossible scenarios.
- Use established design patterns when they prevent tangled control flow or repeated ad hoc logic; don't add patterns preemptively.
- Use dependency injection when it makes dependencies explicit, improves readability, or simplifies testing; avoid hidden globals and hard-coded service construction in business logic.
- Default to a module-based file structure. Split code into separate files when responsibilities diverge, and move any function or component reused by multiple modules into its own shared file.
- Implement one function per file maximum.
- Use a one-word filename in 99% of cases; use longer names only when existing conventions or clarity require it.
- If you write 200 lines and it could be 50, rewrite it.
Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
3. Surgical Changes
Touch only what you must. Clean up only your own mess.
When editing existing code:
- Don't "improve" adjacent code, comments, or formatting.
- Don't refactor things that aren't broken.
- Match existing style, even if you'd do it differently.
- Don't add code comments unless the user explicitly asks for them.
- If you notice unrelated dead code, mention it - don't delete it.
- When implementing a new feature, do not use patch-style or workaround implementations; implement the requested behavior directly in the relevant code, and do not create or run migrations unless explicitly requested.
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 · 92 lines · 957 tokens per session scan A 677958ccb917
friday AGENTS.md is an instructions file published in the GitHub repository HaraldBregu/friday (10 stars, last pushed 4d ago), licensed MIT. It adds 957 tokens to every session, about $0.0048 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
personal-model AGENTS.md
Instructions for Intuition-Lab/personal-model, covering agents.md, runtime boundary, commands, pipeline and documentation map.
lobu AGENTS.md
Instructions for lobu-ai/lobu, covering repo map, unrecoverable — never do these, facts you cannot derive, ship a change and how to work.
ZhiWei CLAUDE.md
Instructions for ntygod/ZhiWei, covering claude.md, project overview, build & development commands, backend and frontend.
openmozi AGENTS.md
Instructions for spytensor/openmozi, covering agents.md — repository instructions for coding agents, non-negotiable rules, mandatory bug and feedback workflow, practical implications and scope, simplicity, and test discipline.
outsystems-mcp CLAUDE.md
Claude Code instructions for OutSystems/outsystems-mcp, covering claude.md, supported harnesses, validate every change against every supported harness, skill docs must stay in lockstep across hosts and check before opening a pr.
future-os CLAUDE.md
Claude Code instructions for futuregene/future-os, covering claude.md, workspace layout, project memory, development workflow and before opening a pr.