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/deltawi/deltallm/agents-mdgit clone --depth 1 https://github.com/deltawi/deltallmWrote 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/deltawi/deltallm/agents-md)<a href="https://agentmods.dev/instructions/deltawi/deltallm/agents-md"><img src="https://agentmods.dev/badge/instructions/deltawi/deltallm/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 | $0.00229 | $0.00229 |
| Opus 5 | $0.00114 | $0.00114 |
| Sonnet 5 | $0.00046 | $0.00046 |
| Haiku 4.5 | $0.00023 | $0.00023 |
Grade A, and why
deltallm 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.
What it actually says
Repository Instructions
Required first step
Before analyzing, planning, editing, running project commands, or reviewing changes, read RULES.md completely. It is the canonical repository-wide engineering contract and applies to every task in this repository.
RULES.md is larger than some agents' automatically loaded instruction limit. Open the file directly and continue reading in chunks until the end; do not rely on a truncated view, excerpt, or prior summary.
If RULES.md is missing or cannot be read completely, stop and report the problem before changing the repository.
Precedence and maintenance
- Follow system and user instructions first, then the applicable repository guidance.
- More local
AGENTS.mdorAGENTS.override.mdfiles may add context or tighten requirements for their subtree, but must not weaken or contradictRULES.md. - Keep this file as a small discovery/bootstrap pointer. Do not duplicate the engineering rules here.
- Do not edit
AGENTS.mdorRULES.mdmerely to make another change easier. Governance changes require explicit scope, rationale, and review.
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 · 17 lines · 229 tokens per session scan A 4da0256d1f0f
deltallm AGENTS.md is an instructions file published in the GitHub repository deltawi/deltallm (19 stars, last pushed yesterday), licensed MIT. It adds 229 tokens to every session, about $0.0011 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
ai-gateway AGENTS.md
AGENTS.md instructions for ferro-labs/ai-gateway, covering agents.md, project overview, current development snapshot, public-facing wording and build, test, and run commands.
tiygate AGENTS.md
Instructions for tiylabs/tiygate, covering repository guidelines, project structure & module organization, engineering principles, build, test, and development commands and coding style & naming conventions.
awesome-ai-gateway CLAUDE.md
Claude Code instructions for cuihuan/awesome-ai-gateway, covering claude.md — working rules for this repository, what this repository is, the two goals — judge every change against these, non-negotiable rules and before you commit.
sbproxy AGENTS.md
Instructions for soapbucket/sbproxy, covering sbproxy (rust workspace), pre-commit checks, changelog entries are fragments, not changelog.md edits, the gate validates the working tree; git push ships head and running the gate.
inferrail CLAUDE.md
Claude Code instructions for domondi1/inferrail, covering inferrail — agent context, before major feature work, read, before implementing something substantial, ask, engineering rules and repo-level conventions.
sbproxy CLAUDE.md
Instructions for soapbucket/sbproxy, covering sbproxy (rust workspace), pre-commit checks, changelog entries are fragments, not changelog.md edits, an insertion can steal the item below it and a filtered test selection that matches nothing exits 0.