Borrowing it
Nothing to install: this file belongs to prebid/salesagent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/prebid/salesagent/main/CLAUDE.mdgit clone --depth 1 https://github.com/prebid/salesagentWrote 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/prebid/salesagent/claude-md)<a href="https://agentmods.dev/instructions/prebid/salesagent/claude-md"><img src="https://agentmods.dev/badge/instructions/prebid/salesagent/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/prebid/salesagent/claude-md"><img src="https://agentmods.dev/badge/instructions/prebid/salesagent/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.12301 | $0.12301 |
| Opus 5.5 | $0.04920 | $0.04920 |
| Sonnet 5.5 | $0.02460 | $0.02460 |
| Haiku 4.5 | $0.01230 | $0.01230 |
Grade A, and why
salesagent 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 27d 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.
fetch(apiUrl, { credentials: 'same-origin' }); How it starts
The opening of the file, as written. The whole thing — 691 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prebid Sales Agent development guide
🤖 For Claude (AI assistant)
This guide surfaces the repository-specific rules for the Prebid Sales Agent codebase (maintained under Prebid.org). The 11 critical patterns and the structural guards that enforce them are non-negotiable; the § Documentation list at the end says where the depth lives.
Never push directly to main. Commits and PR titles use Conventional Commits prefixes — feat / fix / docs / refactor / perf / chore — enforced by .github/workflows/pr-title-check.yml; release-please builds the changelog from them, so an unprefixed commit ships undocumented.
Common task patterns
- Adding a new AdCP tool: Extend library schema → Add
_impl()controller → Add aToolSpecrow tosrc/core/tools/registry.py→ Add tests. MCP registration, the A2A card and the REST route are all generated from the row. - Fixing a route issue: Check for conflicts with
grep -r "@.*route.*your/path"→ Useurl_for()in Python,scriptRootin JavaScript - Modifying schemas: Verify against AdCP spec → Update Pydantic model → Run
pytest tests/unit/test_adcp_contract.py - Database changes: Reach the data through a repository inside a Unit of Work → Use
JSONTypefor JSON columns → Create migration withalembic revision - Any feature or bug fix: TDD — the failing test comes first, and every change is gated by
make quality(full cycles in.claude/rules/workflows/tdd-workflow.mdandbug-reporting.md) - Refactorings: additionally run
tox -e integrationand verify imports withuv run python -c "from module import thing"— pre-commit hooks can't catch import errors
Key files to know
src/core/main.py— MCP server and tool registrationsrc/core/tools/— tool_impl()controllers and services (package)src/core/tools/registry.py—TOOLS: the one declaration every transport derives fromsrc/core/tools/_boundary.py— the one path from a validated request to a responsesrc/core/schemas/— Pydantic models, AdCP-compliant (package)src/adapters/base.py— adapter interfacesrc/adapters/gam/— GAM implementationtests/unit/test_adcp_contract.py— schema compliance tests
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.
- 27d ago Changed · +4 lines · +84 tokens per session 23df8f0eba62
- 1mo ago Changed · +1 lines · +126 tokens per session 9d472f3046f3
- 1mo ago Changed · +224 lines · +4,759 tokens per session 364c61d6b164
- 1mo ago Changed · -305 lines · -1,236 tokens per session a28cdf96a2c0
- 1mo ago First seen · 767 lines · 8,568 tokens per session scan A 9d571ebf5916
salesagent CLAUDE.md is an instructions file published in the GitHub repository prebid/salesagent (39 stars, last pushed yesterday), licensed Apache-2.0. It adds 12,301 tokens to every session, about $0.0492 per session on Opus 5.5. 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 2026-09-01.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.