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/lkoelman/githueber/agents-mdgit clone --depth 1 https://github.com/lkoelman/githueberWrote 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/lkoelman/githueber/agents-md)<a href="https://agentmods.dev/instructions/lkoelman/githueber/agents-md"><img src="https://agentmods.dev/badge/instructions/lkoelman/githueber/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 | $0.00911 | $0.00911 |
| Opus 5 | $0.00456 | $0.00456 |
| Sonnet 5 | $0.00182 | $0.00182 |
| Haiku 4.5 | $0.00091 | $0.00091 |
Grade A, and why
githueber 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rules
Test-Driven Development (TDD) Workflow
Strong preference for TDD; Agent should guide this workflow proactively.
TDD Steps
-
Write failing test first (before any implementation)
- Add test case to appropriate test file in package
- Run pytest to confirm test fails with expected error
- Commit the failing test (optional but recommended for clarity)
-
Implement minimal code to pass test
- Write only enough code to make the test pass
- Avoid over-engineering or extra features
-
Run tests again
- pytest should now pass
- If not, iterate on implementation
-
Refactor if needed
- Keep tests passing while improving code
- Run pytest after each refactor
-
Repeat for next behavior
When TDD is impractical:
- Document why (e.g., characterization test requires understanding existing behavior first)
- Use characterization tests: write tests that capture current behavior, then refactor safely
- Still aim for test coverage of new/changed code
Test coverage expectations:
- New behavior: must have tests
- Bug fixes: add regression test that would have caught the bug
- Refactors: existing tests must still pass; add tests if coverage gaps exist
Editing and Change Discipline
Hard Rules
- Read before writing: NEVER propose changes to code you haven't read. Use Read tool first.
- No surprise changes: Only make changes directly requested or clearly necessary for the task.
- Smallest scope first: Build/test single modules or packages before workspace-wide operations.
- Preserve documentation comments: Keep existing documentation comments when editing code. If a comment becomes inaccurate, rewrite it to match the new behavior; do not remove documentation comments without replacing them with accurate documentation.
What NOT to do (unless explicitly requested)
- Add features beyond what was asked
- Refactor surrounding code "while you're there"
- Add docstrings, comments, or type annotations to unchanged code
- Add error handling for scenarios that can't happen
- Create helpers/utilities for one-time operations
- Design for hypothetical future requirements
- Add backwards-compatibility hacks (e.g., renaming unused
_vars, re-exporting types,// removedcomments) - Delete unused code without confirming it's truly unused
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 · 106 lines · 911 tokens per session scan A cdaf8215bdda
githueber AGENTS.md is an instructions file published in the GitHub repository lkoelman/githueber (2 stars, last pushed 4mo ago), licensed MIT. It adds 911 tokens to every session, about $0.0046 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
sand AGENTS.md
AGENTS.md instructions for onorbumbum/sand, covering core beliefs by phase, interaction style, coding assistance and key references.
co-evolution CLAUDE.md
Instructions for alanshurafa/co-evolution, covering co-evolution - cross-ai document refinement, default rule, components, co-evolution skill (skills/co-evolution/) and co-evolve bouncer (co-evolve-bouncer.sh).
babysitter CLAUDE.md
Claude Code instructions for a5c-ai/babysitter, covering claude.md, repo-specific overrides, read these first, quick commands and claude code local notes.
co-evolution AGENTS.md
Instructions for alanshurafa/co-evolution, covering for agents reading this repo, the two markers, how to interact with this repo, lab features and project context (gsd-managed).
gh-stars-classifier-skill AGENTS.md
Instructions for catuscio/gh-stars-classifier-skill, covering github stars classifier — agent workflow, when to invoke, prerequisites (check first, fail fast), root resolver (run once, before any phase) and workflow.
codex-skill AGENTS.md
AGENTS.md instructions for Mauriciog87/codex-skill, covering sol-luna orchestration, model roles, durable control plane, concurrency and exclusive ultra takeover.