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/declade/lucairn-sdks/claude-mdgit clone --depth 1 https://github.com/Declade/lucairn-sdksWrote 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/declade/lucairn-sdks/claude-md)<a href="https://agentmods.dev/instructions/declade/lucairn-sdks/claude-md"><img src="https://agentmods.dev/badge/instructions/declade/lucairn-sdks/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 | $0.00397 | $0.00397 |
| Opus 5 | $0.00198 | $0.00198 |
| Sonnet 5 | $0.00079 | $0.00079 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
lucairn-sdks 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 5d 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.
What it actually says
Merge Workflow
- Do NOT use
gh pr merge --squash --delete-branch— it fails on the local checkout step in this environment. - Use separate commands:
gh pr merge --squashthengit branch -d <branch>. Or merge via the GitHub UI. - Always run subagent pre-commit review checks before committing. Do not skip on "simple" commits. If no relevant subagent exists for the diff, say so explicitly before committing.
Server & Deploy Conventions
- For server 116 and other production hosts, look up the SSH user and key from Obsidian/memory before attempting connection. Do not try default credentials.
- When restarting docker compose services, always include the required override files (e.g. the overlay that sets VEIL_TSA_URL, VEIL_REKOR_URL, and TRACEVAULT_* vars). Omitting overrides silently wipes environment variables and has caused deploy outages.
- Use pnpm, not npm, for any repo with pnpm-lock.yaml. Using npm in a pnpm repo has caused a production outage.
Review & Verification Gates
- After implementing changes, run the appropriate subagent review (bug-hunter, security-review, or equivalent) BEFORE opening a PR. Past sessions have caught log-injection, null-JSON 500s, and route-ordering bugs at this gate.
- Honor literal string requirements exactly. Do not substitute (e.g. use the literal
'22'pin rather thannode-version-file; do not introduce forbidden tokens likePro+that trip the CI banlist). - Before executing any multi-phase plan, restate: (1) the exact scope, (2) any ambiguous terms you would interpret, (3) which repo, branch, or server you will touch. HALT and wait for confirmation if the prompt looks truncated or any premise is unclear. Do not proceed on best-guess.
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.
- 5d ago First seen · 18 lines · 397 tokens per session scan A c4a6e3d6836c
lucairn-sdks CLAUDE.md is an instructions file published in the GitHub repository Declade/lucairn-sdks (2 stars, last pushed 14d ago), licensed MIT. It adds 397 tokens to every session, about $0.0020 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 2026-08-31.
Other instructions, from other repositories
webspace_app CLAUDE.md
Claude Code instructions for theoden8/webspace_app, covering claude.md, style (output, code, commits), git, sandbox bootstrap and fvm — required (.fvmrc pins flutter 3.38.6).
awsmux AGENTS.md
Instructions for 0hardik1/awsmux, covering agents.md, what awsmux is, build, test, verify, layout and the safety model — invariants you must not weaken.
plan-forge naming.instructions.md
Azure naming conventions — Microsoft CAF abbreviations, constraints, uniqueness, tagging.
agent-skills fortrabbit.instructions.md
Instructions for fortrabbit/agent-skills, covering fortrabbit — github copilot instructions, what fortrabbit is, configuration lookup, available operations and mcp server (optional).
forgetted AGENTS.md
Instructions for hermes-labs-ai/forgetted, covering agents.md — forgetted, role, commands, project structure and testing.
cron-mcp CLAUDE.md
Claude Code instructions for Shreyas-Profile/cron-mcp, covering deploying cron-mcp to hetzner + regiq.in, server (shared with the rest of the globalion mcp fleet), deploy a new version, first-time subdomain wiring (cron.regiq.in) and env vars.