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/vedsoni-dev/primer/claude-mdgit clone --depth 1 https://github.com/VedSoni-dev/primerWhat 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 | $0.01257 | $0.01257 |
| Opus 5 | $0.00629 | $0.00629 |
| Sonnet 5 | $0.00251 | $0.00251 |
| Haiku 4.5 | $0.00126 | $0.00126 |
Grade A, and why
primer 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 2d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Context for any Claude Code session working in this repository. Read this file fully before making changes. It states what this project is, the doctrine that governs it, and the rules that no refactor, feature, or pipeline may move.
What this repository is
primer is an open learner record plus an MCP server. One SQLite file per family, on the family's machine, holding everything one child knows, struggles with, cares about, and how they learn. An AI tutor (Claude, via the parent's own Claude Code login) reads the record between sessions, builds a one-off HTML activity, and queues it for parent approval. The child never talks to a model. The record is what lasts.
The project answers Y Combinator's RFS "The Primer" while rejecting its dangerous half: no company should own a decade of a child's most intimate learning data. The open version must exist before proprietary lock-in accretes.
The doctrine
One sentence governs every architectural decision:
The Record knows the child. The World knows the field. The humans know the goal. The tutor is the only place the three are allowed to meet.
- The Record is the per-family SQLite file. Mastery, misconceptions, interests, accommodations, affect, evidence. It never leaves the family's machine.
- The World is versioned, reviewed, public data shipped with primer
releases: curriculum packs, prerequisite edges, pedagogy claims with
citations, parameter priors, and interest lenses. It is an artifact, never a
service. See
docs/WORLD.md. - The goal is human-set intent. The
goaltable is written by parents and teachers. Theinteresttable is revealed by the child and decays if unreinforced. The tutor reads both. Nothing else sets direction. - The tutor composes all three at planning time, on the family's machine, with no network access.
The composition rule that follows, stated as doctrine and pinned by an invariant test:
The World proposes. The Record and the humans dispose. Nothing in The World may target, rank, or select content for an individual child. Which lens activates, which skill comes next, what the session looks like: those decisions are made by the scheduler and the tutor on the family's machine, as a function of the Record and the human-set goals. The World is a menu. It is never a hand on the child's back.
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.
- 2d ago First seen · 108 lines · 1,257 tokens per session scan A de29c9b8b454
primer CLAUDE.md is an instructions file published in the GitHub repository VedSoni-dev/primer (1 stars, last pushed 27d ago), licensed Apache-2.0. It adds 1,257 tokens to every session, about $0.0063 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.