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/blisspixel/primr/claude-mdgit clone --depth 1 https://github.com/blisspixel/primrWrote 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/blisspixel/primr/claude-md)<a href="https://agentmods.dev/instructions/blisspixel/primr/claude-md"><img src="https://agentmods.dev/badge/instructions/blisspixel/primr/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 | $0.02646 | $0.02646 |
| Opus 5 | $0.01323 | $0.01323 |
| Sonnet 5 | $0.00529 | $0.00529 |
| Haiku 4.5 | $0.00265 | $0.00265 |
Grade A, and why
primr CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
urllib) for scrape-tier evasion - that set is **closed**. A sixth client is a How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - the contract for building primr
You are working on the primr codebase. This file is the development
contract and context map: read it before writing code. It is the canonical
guide for any contributor (human or agent); Claude Code loads it natively, and
docs/CONTRIBUTING.md points other tools here.
Not to be confused with
AGENTS.md, which is a product artifact: it tells agents how to operate the primr CLI/MCP for research. This file is about changing primr's source. If you are here to run research, you want AGENTS.md, not this.
The bar: code any human or AI could admire - tidy, consistent, secure, well-tested. We are not making slopware. The rules below exist because AI-assisted code reliably regresses on exactly these axes (duplication, inconsistent patterns, stale APIs, silent insecurity) unless held to a contract.
Quick Start
primr turns a company name and website into sourced, long-form strategic
reports. It is a CLI-first, local-first Python package (src/ layout), an LLM
API client + adaptive scraper + MCP/A2A agent - it trains and serves no
models. To work on it:
The enduring product boundary is the
Company Analyst Product Contract:
the bare company-and-website invocation must produce exceptional researched,
long-form Strategic Overview and YAML-defined strategy artifacts as reliable
Word and Markdown files. Architecture, routing, ledgers, memory, and agent
surfaces are supporting capabilities, not replacement products.
- Set up the dev env (
uv sync --locked --extra dev --extra api, thenuv run playwright install chromium) - seedocs/CONTRIBUTING.md. - Put code in the package that owns it (see Architecture Pointers). Use the existing seam rather than inventing a second way to do the same thing.
- Before opening a PR, run the Verification Commands and re-read the Negative Constraints. New code ships with tests; the coverage ratchet only rises.
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 · 208 lines · 2,646 tokens per session scan A 98d1328830e4
primr CLAUDE.md is an instructions file published in the GitHub repository blisspixel/primr (3 stars, last pushed 3d ago), licensed Apache-2.0. It adds 2,646 tokens to every session, about $0.0132 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
Autosearch CLAUDE.md
Instructions for 0xmariowu/Autosearch, covering autosearch — project rules, what this is, local test (run before push), session checklist and workflow.
Autosearch copilot-instructions.md
Instructions for 0xmariowu/Autosearch, covering copilot instructions for agentlint, hard rules — never violate, scope discipline for this repo, commit and pr format and ci-fix specific rules (ci-doctor / @copilot fix ci).
synapse-research CLAUDE.md
Claude Code instructions for NimbleBrainInc/synapse-research, covering synapse-research, architecture, commands, install server deps and install ui deps + build.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal 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).
intervals-icu-mcp CLAUDE.md
Instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.