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/muratsilahtaroglu/claude-code-starter-kit/claude-mdgit clone --depth 1 https://github.com/muratsilahtaroglu/claude-code-starter-kitWrote 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/muratsilahtaroglu/claude-code-starter-kit/claude-md)<a href="https://agentmods.dev/instructions/muratsilahtaroglu/claude-code-starter-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/muratsilahtaroglu/claude-code-starter-kit/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 | $0.01006 | $0.01006 |
| Opus 5 | $0.00503 | $0.00503 |
| Sonnet 5 | $0.00201 | $0.00201 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
claude-code-starter-kit 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — project constitution (TEMPLATE)
Claude Code reads this first every session. The four
@-imports below auto-load the working rules, the running handover, the lessons database, and the task board — always in context, re-injected from disk after every compaction. Keep this file lean (< ~200 lines); push sometimes-relevant knowledge into.claude/skills/and deterministic checks into.claude/hooks/. Fill in the<...>blanks.
@rules.md @HANDOVER.md @LESSONS.md @TASKS.md
Session protocol (rules.md §9)
- Start: run
/keel-continue(cross-checks the loaded memory against PLAN.md + git, then RESUMES half-done work, TAKES the lane's next assigned item via the comprehension gate, or reports IDLE) — or by hand: read the TOP block ofHANDOVER.md+LESSONS.md+TASKS.md ## Now+ recentgit log; pick ONE## Nowitem; verify tests pass before new work. - During: the moment a rule / must-run test / gotcha / failed approach is agreed or discovered — ask
"shall I note this?" and append it to
LESSONS.mdimmediately (don't wait for compaction). - End (or before compact):
/keel-handover(new HANDOVER block) · delete done TASKS items · commit with approval. If any memory file exceeds its cap →/keel-distill. About to compact manually? Run/keel-compact— it bundles all of the above, verifies freshness, then hands off to/compact. - When compacting, always preserve: the list of modified files, open
TASKS.md ## Nowitems, test commands, and any agreement not yet written toLESSONS.md(write it there first).
What we're building
<Purpose of the project in 2-3 sentences. What problem it solves, who uses it.>
Architecture (summary)
<Components and how they talk to each other. E.g.: API (FastAPI) + Worker + DB + Vector DB + LLM. A text diagram.>
Key decisions (ADRs in docs/adr/)
- <ADR-0001: ...>
- <ADR-0002: ...>
(Every significant technical decision becomes an ADR; copy
docs/adr/0000-adr-template.md.)
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 · 66 lines · 1,006 tokens per session scan A d61f81e00a72
claude-code-starter-kit CLAUDE.md is an instructions file published in the GitHub repository muratsilahtaroglu/claude-code-starter-kit (9 stars, last pushed today), licensed MIT. It adds 1,006 tokens to every session, about $0.0050 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
ai-dial-core CLAUDE.md
Claude Code instructions for epam/ai-dial-core, covering claude.md, build & run, set credentials via environment variables, build (skip tests) and run all tests.
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
technocore-chat AGENTS.md
AGENTS.md instructions for flop-labs/technocore-chat: CI runs exactly these — run them before pushing.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).