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/second-inc/second/agents-mdgit clone --depth 1 https://github.com/Second-Inc/secondWhat 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 | $0.02623 | $0.02623 |
| Opus 5 | $0.01311 | $0.01311 |
| Sonnet 5 | $0.00525 | $0.00525 |
| Haiku 4.5 | $0.00262 | $0.00262 |
Grade A, and why
second 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 yesterday.
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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Second
Second is a generative workspace, which allows teams to build internal tools.
This is a monorepo containing everything.
Layout
- apps/web: nextjs + shadcn
General instructions (not necessarlly task dependent)
For big tasks (or whenever you feel like it), please first of all read the docs/ to understand about this project. Read them also to orient yourself in this project, find relevant files, understand the overall architecture and the code base. Obviously they might be outdated so the code is the real truth eventually.
In this repo, identify key files, the architecture, what this project is about, and how everything works (in they way which is relevant for this task) using the docs/.
Remember that we have currently 2 deployment models:
- Local, using
npx @second-inc/cli ... - On prem - on GCP (AWS is also not currently supported but it will and should be sometime). On prem can be either on the customer's cloud OR a managed instance - where I deploy it on Second's cloud and help them register the Auth provider, etc.
We are now in the open source repo. You should probably only work on the open source repo (this was just context for you).
Also important: Whatever you do, it's very important that this will be enforced securely and beautifully and will actually work and will not have any security issues. Also keep in mind tenant isolation (critical). I mean I know that right now we haven't released our SAAS solution yet, but still it's very important. Keep all of the best practices from the docs and the current structure.
It's also very important to keep everything very secure and go with the security best practices and everything that we currently have set up and fixed to not regress and to not introduce any security issues.
About app UI changes
- Before changing app UI, inspect strong local references such as
apps/web/src/components/ai-elements/tool-card.tsx,apps/web/src/components/ai-elements/agents-card.tsx,apps/web/src/app/w/[workspaceId]/apps/[appId]/agents/page.tsx, andapps/web/src/app/w/[workspaceId]/settings/integrations/page.tsx. - Match the existing restrained shadcn/Radix theme: compact rows, muted borders, mono metadata, semantic badges, and polished tool-call / agent-card patterns.
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.
- yesterday First seen · 103 lines · 2,623 tokens per session scan A ffd0709c5c49
second AGENTS.md is an instructions file published in the GitHub repository Second-Inc/second (76 stars, last pushed 11d ago), licensed Apache-2.0. It adds 2,623 tokens to every session, about $0.0131 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
kaneo AGENTS.md
Instructions for usekaneo/kaneo, covering kaneo agent guide, principles, architecture, boundaries that must hold and follow a change through.
kaneo CLAUDE.md
Instructions for usekaneo/kaneo, a project described as: 🎯 All you need. Nothing you don't. Open source project management that works for you, not against you.
n8n AGENTS.md
AGENTS.md instructions for n8n-io/n8n, covering agents.md, project overview, general guidelines, agent skills and claude code plugin and essential commands.
n8n CLAUDE.md
Claude Code instructions for n8n-io/n8n, a project described as: Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
ui-beats AGENTS.md
Instructions for nikhils4/ui-beats: This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in nodemodules/next/dist/docs/ (resolved from this file's directory; in monorepos the next package may not be visible from the repo root) before…
bytechef CLAUDE.md
Claude Code instructions for bytechefhq/bytechef, covering claude.md, repository overview, essential development commands, server development and build and compile the project.