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/duane1024/l123/agents-mdgit clone --depth 1 https://github.com/duane1024/l123Wrote 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/duane1024/l123/agents-md)<a href="https://agentmods.dev/instructions/duane1024/l123/agents-md"><img src="https://agentmods.dev/badge/instructions/duane1024/l123/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 | $0.01398 | $0.01398 |
| Opus 5 | $0.00699 | $0.00699 |
| Sonnet 5 | $0.00280 | $0.00280 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
l123 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 3d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — L123 project guide
Session-level conventions for working on L123 (a Lotus 1-2-3 R3.4a for DOS TUI clone). Living document — edit freely as conventions emerge.
Canonical docs — read these before making decisions
docs/SPEC.md— what L123 is. Scope, modes, menu tree, authenticity contract.docs/PLAN.md— implementation milestones, risk register, test strategy.docs/MENU.md— complete menu tree; source of truth forl123-menu.
If code and doc disagree, fix the doc first, then write code to match.
How we develop: red / green / refactor (strict TDD)
Test-first, always. Every change to shipping code follows this loop:
1. Red
Write the failing test(s) that describe the behavior you want. Run them.
They must fail for the right reason — not a compile error, not a
panic from unrelated setup. cargo test -p <crate> shows a clean
failure in the new test, pointing at the behavior being specified.
If you can't figure out what the test should assert, the behavior isn't specified enough yet. Re-read SPEC, or write the acceptance transcript first, then come back.
2. Green
Write the minimum code to make the tests pass. No refactoring, no extra features, no speculative abstractions, no helpers you "might need later." If a test is green before you meant it to be, delete the extra code until only the test's claim is covered.
3. Refactor
Now, and only now, clean up. Re-run tests after every small refactor
step. Never refactor with red tests. Clippy must stay clean:
cargo clippy --workspace --all-targets -- -D warnings.
Exceptions (be honest — they should be rare)
- Pure docs/comment changes.
- Throwaway spikes — must be marked
WIP: spikeand deleted before landing. Any code you keep must have tests written before it.
Test tiers
Every feature lands with tests at one or more of:
- Unit tests — colocated with source (
#[cfg(test)] mod tests). Pure-function tests; no ratatui, no IronCalc. - Engine integration tests —
crates/l123-engine/src/ironcalc_adapter.rsunder#[cfg(test)]. Drive theEnginetrait against real IronCalc. - Acceptance transcripts —
tests/acceptance/*.tsv, run bycrates/l123-ui/tests/acceptance.rs. Keystrokes in, on-screen state out. Every item in SPEC §20 "Authenticity Contract" gets ≥1 transcript before the claim can be called done.
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.
- 3d ago First seen · 149 lines · 1,398 tokens per session scan A b619041ed1be
l123 AGENTS.md is an instructions file published in the GitHub repository duane1024/l123 (128 stars, last pushed 3mo ago), licensed MIT. It adds 1,398 tokens to every session, about $0.0070 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
wallfacer CLAUDE.md
Instructions for changkun/wallfacer: If you didn't add a test, you didn't fix a bug. Every bug fix must include a reproducible test that fails without the fix and passes with it. You commit frequently, one small scope diff at a time. Push to main once a full batch of work is complete and verified. Leftover must be…
spec-driven-tdd AGENTS.md
Instructions for strelov1/spec-driven-tdd: This repo is a skill-pack. When implementing an OpenSpec change, invoke the spec-driven-tdd skill and follow its lifecycle: plan in OpenSpec, isolate in a worktree, implement each task via TDD → simplify → review, then finish + archive.
mcp-repo-onboarding AGENTS.md
Instructions for rogermt/mcp-repo-onboarding, covering agents.md — agent & copilot instructions, current status, output verification, project identity and ⚠️ critical: tdd required.
arxiv-agent-mcp AGENTS.md
AGENTS.md instructions for tbaraniuk/arxiv-agent-mcp, covering agents.md, roles, test-writer, implementer and per-task loop.
think CLAUDE.md
Instructions for matiasvillaverde/think, covering claude.md, quick reference, hierarchical documentation, development philosophy and test-driven development (tdd).
opencode-copilot-instructions AGENTS.md
AGENTS.md instructions for ekroon/opencode-copilot-instructions, covering agent instructions, orchestration pattern, 1. always orchestrate (unless being orchestrated), 2. test-driven development (tdd) and tdd workflow for each module.