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/jonradoff/lastsaas/claude-mdgit clone --depth 1 https://github.com/jonradoff/lastsaasWrote 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/jonradoff/lastsaas/claude-md)<a href="https://agentmods.dev/instructions/jonradoff/lastsaas/claude-md"><img src="https://agentmods.dev/badge/instructions/jonradoff/lastsaas/claude-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 | $0.00556 | $0.00556 |
| Opus 5 | $0.00278 | $0.00278 |
| Sonnet 5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
lastsaas CLAUDE.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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LastSaaS Development Rules
Validation
LastSaaS uses hybrid validation: Go-side (validate struct tags via go-playground/validator) and MongoDB JSON Schema (internal/db/schema.go).
When modifying model structs in internal/models/:
- Update
validatestruct tags on the model - Update the corresponding MongoDB JSON Schema in
internal/db/schema.go - Keep both in sync — the Go tags and MongoDB schema must enforce the same constraints
- Run
cd backend && go test ./internal/validation/...to verify
When adding a new collection that accepts user/API writes:
- Add
validatetags to the model struct - Add a schema function to
internal/db/schema.goand include it inAllSchemas() - Add tests in
internal/validation/validate_test.go
System Logging
Use syslog.Logger for all significant system events. Severity levels: critical, high, medium, low, debug.
Build Verification
Always verify after changes:
cd backend && go build ./...
cd frontend && npx tsc --noEmit
Dependent Project Deployment (CRITICAL)
Any project built on the LastSaaS boilerplate — whether using it as a Git submodule, fork, or copy — MUST deploy using the SaaS Dockerfile (Dockerfile.saas) and the corresponding Fly config (fly.saas.toml). Never use bare fly deploy on a project that depends on LastSaaS.
Why this matters: The SaaS Dockerfile runs both the product backend AND the LastSaaS backend behind Caddy (via supervisord). The LastSaaS backend serves all auth endpoints (/api/auth/*), bootstrap status (/api/bootstrap/status), OAuth providers (Google, etc.), billing, and admin APIs. Without it, login breaks silently — the product backend has no auth routes, so API calls return HTML from the SPA catch-all, causing mysterious redirects to /setup or broken login forms with missing OAuth buttons.
Correct deploy command:
fly deploy -c fly.saas.toml
Propagation rule: When setting up or working on any dependent project, ensure:
- The project has a
deploy.mdat its root with full deployment instructions and the "why" behind the multi-process architecture - The project's Claude Code memory (MEMORY.md or CLAUDE.md) contains a cross-reference: "See
deploy.md— never barefly deploy" - If the project doesn't have these yet, create them before the first deployment
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 · 45 lines · 556 tokens per session scan A b947a7b5e5e4
lastsaas CLAUDE.md is an instructions file published in the GitHub repository jonradoff/lastsaas (165 stars, last pushed 6mo ago), licensed MIT. It adds 556 tokens to every session, about $0.0028 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
gridctl AGENTS.md
Instructions for gridctl/gridctl, covering agents.md, what gridctl is, build and run, code architecture and constitution.
gopls-mcp CLAUDE.md
Instructions for xieyuschen/gopls-mcp, a project described as: MCP server for golang projects development: Expand AI Code Agent ability boundary to have a semantic understanding and determinisic information for golang projects.
symbolpeek-mcp CLAUDE.md
Instructions for pioner92/symbolpeek-mcp: SymbolPeek's whole value is context economy: an agent gets one symbol, not the file. The rule applies to the code too — including this file, which loads into every session, so hold it to its own bar.
go-job CLAUDE.md
Instructions for anatolykoptev/go-job, a project described as: Job, Remote & Freelance Search MCP server.
yandex-mcp AGENTS.md
Instructions for n-r-w/yandex-mcp, covering project specific rules and information, yandex services supported, tech stack, instructions and golang rules.
mcp-ratchet AGENTS.md
Instructions for hexxla/mcp-ratchet, covering project instructions, your responsibilities as an agent, hexagonal architecture, core concepts and layer responsibilities & rules.