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/tesslateai/opensail/claude-mdgit clone --depth 1 https://github.com/TesslateAI/OpenSailWrote 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/tesslateai/opensail/claude-md)<a href="https://agentmods.dev/instructions/tesslateai/opensail/claude-md"><img src="https://agentmods.dev/badge/instructions/tesslateai/opensail/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 5.1 | $0.06204 | $0.06204 |
| Opus 5 | $0.03102 | $0.03102 |
| Sonnet 5 | $0.01241 | $0.01241 |
| Haiku 4.5 | $0.00620 | $0.00620 |
Grade A, and why
OpenSail 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 6d 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 — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Never add claude as a contributor to github.
You are a senior level coding agent. You will apply real world solutions to all the problems, fixing them in such a way where you do not cheat the solution, break existing functionality, and are scoped in. The solutions you write must be scalable and for the future, not fixing or hardcoding.
CRITICAL RULE: Investigation is READ-ONLY
When the user describes an issue, pastes an error, asks a question, or says "investigate" / "dive deep" / "look into":
- ONLY read files, search code, and explain findings in text
- NEVER edit, write, or modify any code or infrastructure
- ALWAYS ask "Want me to implement this?" before touching anything
- This is NON-NEGOTIABLE. Violating this is a session-ending event.
Always read through the docs/ to find items it is a knowledgegraph
Research Folder
The research/ directory is gitignored and contains cloned repos for reference/research:
research/hermes-agent/— NousResearch/hermes-agent — Hermes agent framework
Use subagents generously if you are doing bulk task items that have a small / atomic scope.
don't do conditional logic for k8s and docker implementation differences. try to keep it as similar as possible unless if a platform requires differeces. Prioritize the k8s (keep that logic more intact than docker. )
On windows use MSYS_NO_PATHCONV=1 while running kubectl or docker exec commands. The ECR IS <AWS_ACCOUNT_ID> not <AWS_ACCOUNT_ID>
CRITICAL: kubectl Context Safety — EVERY kubectl command MUST include --context=<name>. NEVER use kubectl config use-context, ./scripts/kctx.sh, or any context-switching command. Context switching is BANNED because cronjobs and other processes can change it mid-session, causing accidental production mutations. Use: kubectl --context=tesslate (minikube), kubectl --context=tesslate-production-eks (prod), kubectl --context=tesslate-beta-eks (beta). See docs/infrastructure/kubernetes/CLAUDE.md for details.
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.
- 6d ago First seen · 394 lines · 6,204 tokens per session scan A 7951622de628
OpenSail CLAUDE.md is an instructions file published in the GitHub repository TesslateAI/OpenSail (638 stars, last pushed 4d ago), licensed Apache-2.0. It adds 6,204 tokens to every session, about $0.0310 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
claude-for-strategy CLAUDE.md
Claude Code instructions for daddia/claude-for-strategy, covering claude.md, layout, validation — run before opening a pr, 2. json sanity and 3. consulting reference mirrors.
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
hatch3r CLAUDE.md
Claude Code instructions for hatch3r/hatch3r, covering hatch3r — development instructions, architecture, development commands, two-axis pillar framework (2.0.0) and orchestrator self-discipline (bypass protection).
aeon CLAUDE.md
Claude Code instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
nextjs-skills CLAUDE.md
Instructions for mohamed-hossam1/nextjs-skills: All contribution rules — style, naming, file layout, verification — live in AGENTS.md. Read that first.
nocturnusai CLAUDE.md
Claude Code instructions for Auctalis/nocturnusai, covering claude.md, project overview, build & run commands, build all modules and run the http api server (port 9300).