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/robconery/kolea/claude-mdgit clone --depth 1 https://github.com/robconery/koleaWrote 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/robconery/kolea/claude-md)<a href="https://agentmods.dev/instructions/robconery/kolea/claude-md"><img src="https://agentmods.dev/badge/instructions/robconery/kolea/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 | $0.01794 | $0.01794 |
| Opus 5 | $0.00897 | $0.00897 |
| Sonnet 5 | $0.00359 | $0.00359 |
| Haiku 4.5 | $0.00179 | $0.00179 |
Grade A, and why
kolea 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 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🐦 Kōlea
Self-hosted email — broadcasts, transactional sends, and drip sequences in one Cloudflare Worker, replacing a paid ESP so the list and engagement data stay owned.
Named for the Pacific golden plover: three thousand miles of open ocean, nonstop, and it lands in the same yard every year. Delivery, and the same address, every time.
Single operator. Not multi-tenant, no visual builder, no self-run SMTP. See docs/PROJECT.md.
Domain: email marketing / transactional email.
Cloudflare resources (Worker, D1, queues) are still named
big-mailer. That is deliberate — they are bound to live production data. Kōlea is the brand,big-maileris the infrastructure. Don't "fix" the mismatch without a cutover plan.
📚 Docs — read before you write
docs/ is the reference set. One doc, one owner. Never write a doc you don't own.
| Doc | What's in it | Read it when | Owner |
|---|---|---|---|
docs/ARCHITECTURE.md |
⭐ The agent's reference. Invariants, system shape, code map, data model, lifecycles, MCP surface, platform limits, recipes, traps. | Before changing any code. Start here. | /design |
docs/SPEC.md |
Numbered, testable behavioral requirements. The reference for intended behavior. | Before changing behavior. Code disagreeing with SPEC is a bug report, not a licence to edit SPEC. | /design |
docs/MEMORY.md |
Decision log — what was chosen, what was rejected, and why. | Before "improving" something odd. The odd thing is usually load-bearing. | /document (appended by all phases) |
docs/INSTALL.md |
Local setup, full production deploy, integrations, troubleshooting. | Setup, deploy, or config questions. | /document |
docs/PROJECT.md |
The problem, who it's for, what's explicitly out of scope. | Before proposing a feature. | /explore |
docs/PLAN.md |
What's built, what's verified, what isn't. | Picking up work. | /plan |
docs/STORIES.md |
Backlog. Currently thin — the build went SPEC → code. | /plan runs. |
/plan |
README.md |
The public front door. | Changing the pitch or the install steps. | /document |
CLAUDE.md |
This file. | /init runs. |
/init |
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 · 123 lines · 1,794 tokens per session scan A 647f2de09b5f
kolea CLAUDE.md is an instructions file published in the GitHub repository robconery/kolea (1 stars, last pushed 4d ago), licensed MIT. It adds 1,794 tokens to every session, about $0.0090 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
flarestarter AGENTS.md
Instructions for FlareStarter/flarestarter, covering agents.md, what this is, structure, conventions and commands.
flarestarter CLAUDE.md
Instructions for FlareStarter/flarestarter: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
supermemory CLAUDE.md
Claude Code instructions for supermemoryai/supermemory, covering claude.md, repository structure, applications (apps/), development commands and root level (monorepo).
email-templates CLAUDE.md
Instructions for ColorlibHQ/email-templates, covering claude.md, repository purpose, layout, commands and editing or adding a template.
saasmail AGENTS.md
AGENTS.md instructions for choyiny/saasmail, covering agent / contributor notes, doc map, tooling, local yarn test prerequisites and ci on every pr.
minshop AGENTS.md
Instructions for ddyy/minshop, covering agents.md — working on minshop, the loop (run this constantly), inspecting local data: use local explorer, not the cli, customizing a cloned shop and architecture in one screen.