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/serac-labs/serac/agents-mdgit clone --depth 1 https://github.com/serac-labs/seracWrote 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/serac-labs/serac/agents-md)<a href="https://agentmods.dev/instructions/serac-labs/serac/agents-md"><img src="https://agentmods.dev/badge/instructions/serac-labs/serac/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 | $0.01554 | $0.01554 |
| Opus 5 | $0.00777 | $0.00777 |
| Sonnet 5 | $0.00311 | $0.00311 |
| Haiku 4.5 | $0.00155 | $0.00155 |
Grade A, and why
serac 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Conventions for this repository. It holds two packages: packages/servicenow-mcp (the MCP server) and
packages/skills (the skill guides), plus .claude-plugin/marketplace.json at the root, which ships the
two together as a Claude Code plugin. There is nothing else.
- The default branch is
main. - Run
bun typecheckfrom the repo root; it runstsgoacross both packages via turbo. - Run tests from a package directory (
cd packages/servicenow-mcp && bun test), orbun run testfrom the root to run both through turbo.bun testat the root is blocked on purpose — seebunfig.toml.
Commits and PR titles
Use conventional commit-style messages and PR titles: type(scope): summary.
Valid types are feat, fix, docs, chore, refactor, and test. Scopes are optional; use mcp,
skills, or ci when it helps.
Examples: fix(mcp): keep tenant scope on cached discovery results, docs: update contributing guide,
chore(skills): add fluent brownfield migration guide.
Style guide
General principles
- Keep things in one function unless composable or reusable.
- Do not extract single-use helpers preemptively. Inline the logic at the call site unless the helper is reused, hides a genuinely complex boundary, or has a clear independent name that improves the caller.
- Avoid
try/catchwhere possible. Prefer.catch(...). - Avoid the
anytype. - Use Bun APIs when possible, like
Bun.file(). - Rely on type inference; avoid explicit type annotations or interfaces unless necessary for exports or clarity.
- Prefer functional array methods (
flatMap,filter,map) overforloops; use type guards onfilterto keep inference downstream. - Add comments for non-obvious constraints and surprising behaviour, not for obvious assignments or control flow. A comment explaining why something is the way it is survives a rewrite; one restating the code does not.
Reduce total variable count by inlining when a value is only used once.
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 · 160 lines · 1,554 tokens per session scan A b9243c103b00
serac AGENTS.md is an instructions file published in the GitHub repository serac-labs/serac (78 stars, last pushed 8d ago), licensed Apache-2.0. It adds 1,554 tokens to every session, about $0.0078 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
now-sdk-ext-mcp CLAUDE.md
Instructions for sonisoft-cnanda/now-sdk-ext-mcp, covering now-sdk-ext-mcp, project overview, architecture, directory structure and sibling projects.
now-sdk-ext-mcp AGENTS.md
Instructions for sonisoft-cnanda/now-sdk-ext-mcp, covering agents.md, what this repository is, hard rules, 1. never write to stdout and 3. adding a tool touches two files, and nothing enforces it.
servicenow-platform-mcp AGENTS.md
Instructions for Xerrion/servicenow-platform-mcp, covering agents.md - servicenow-platform-mcp, 📋 project overview, dependencies, 🚀 setup and 🔧 lint / format / type-check.
mcp-cmdb CLAUDE.md
Claude Code instructions for ketiil/mcp-cmdb, covering servicenow cmdb mcp server, tech stack, project structure, build & run commands and install dependencies.
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
openrouter-mcp-multimodal AGENTS.md
Instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).