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/ellipticmarketing/modelrelay/agents-mdgit clone --depth 1 https://github.com/ellipticmarketing/modelrelayWrote 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/ellipticmarketing/modelrelay/agents-md)<a href="https://agentmods.dev/instructions/ellipticmarketing/modelrelay/agents-md"><img src="https://agentmods.dev/badge/instructions/ellipticmarketing/modelrelay/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 | $0.01514 | $0.01514 |
| Opus 5 | $0.00757 | $0.00757 |
| Sonnet 5 | $0.00303 | $0.00303 |
| Haiku 4.5 | $0.00151 | $0.00151 |
Grade A, and why
modelrelay 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.
Agent Instructions
Post-Feature Testing
After completing any feature or fix, the agent MUST:
- Run
pnpm testto verify the complete unit-test suite passes - If any test fails, fix the issue immediately
- Re-run
pnpm testuntil all tests pass
This ensures the codebase remains in a working state at all times.
Git Commits
When making a commit on behalf of the user, NEVER prefix your commit message with fix:, feature:, feat:, chore:, or any other prefix.
Just write a descriptive sentence of what was changed.
Release Process (MANDATORY)
When releasing a new version, follow this exact process:
- Version Check: Check if version already exists with
git log --oneline | grep "^[a-f0-9]\+ [0-9]" - Version Bump: Update version in
package.json. If the releas only includes bug fixes, bump a patch version (e.g.,0.1.16→0.1.17). If it includes new features, bump a minor version (e.g.,0.1.16→0.2.0) Do not bump the major version. - Commit ALL Changed Files:
git add . && git commit -m "Fixed issue with autostart"- Always commit using a description of what was changed as the commit message.
- Include ALL modified files in the commit (bin/, lib/, test/, README.md, etc.)
- Push:
git push origin master— this repo's release branch ismaster, and GitHub Actions will auto-publish to npm - Create GitHub Release:
(e.g.,gh release create VERSION --title "VERSION" --notes "Release notes"gh release create 1.5.0 --title "1.5.0" --notes "Fixed an issue with ABC") When writing the release notes, summarize the changes from all commits since the last release. - **Wait for npm Publish":
for i in $(seq 1 30); do sleep 10; v=$(npm view modelrelay version 2>/dev/null); echo "Attempt $i: npm version = $v"; if [ "$v" = "0.1.17" ]; then echo "✅ published!"; break; fi; done - Install and Verify:
npm install -g [email protected] - Test Binary:
modelrelay --help(or any other command to verify it works) - Only when the global npm-installed version works → the release is confirmed
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 · 1,514 tokens per session scan A 09b42f1ac8b2
modelrelay AGENTS.md is an instructions file published in the GitHub repository ellipticmarketing/modelrelay (345 stars, last pushed 23d ago), licensed MIT. It adds 1,514 tokens to every session, about $0.0076 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
uview-plus AGENTS.md
AGENTS.md instructions for ijry/uview-plus, covering agents, 提交规范, 发布规范 and uview-plus说明.
heptabase-cli-skills AGENTS.md
Instructions for heptameta/heptabase-cli-skills, covering heptabase-cli-skills, layout, before you commit and releases.
stiletto CLAUDE.md
Instructions for benjamin-bader/stiletto, covering stiletto — contributor & agent guide, commit messages: conventional commits (required), breaking changes, examples and how releases work.
git-authoring AGENTS.md
Instructions for n-shadloo/git-authoring, covering git authoring conventions, usage modes, ground rules, workflow and 1. gather context.
drift drift-push-gates.instructions.md
Nutze diese Instruction, wenn ein Commit, ein Push oder eine Release-Vorbereitung im Drift-Repo ansteht. Sie ist die autoritative Gate-Quelle fuer Pre-Push-Anforderungen, Bypaesse und lokale CI-Pflichten.
cool-test-mcp AGENTS.md
AGENTS.md instructions for CoolTea001/cool-test-mcp, covering agents, commit rules, release & tag rules and documentation & test sync.