senior-engineering-partner: Instructions file for Claude Code

CLAUDE.md

senior-engineering-partner CLAUDE.md is an instructions file for Claude Code from bjgreenberg/senior-engineering-partner. It costs 1,066 tokens per session, scanned A, original, Apache-2.0.

Project instructions for a senior engineering partner skill, including repository structure, pull-request rules, and a required authoring model.

In plain words
What is it for?
Use them when reviewing or proposing changes, or when editing the skill's instructions, references, scripts, tests, or documentation.
Why use it?
They prevent agents from editing protected files with the wrong model and clarify which project documents and checks apply.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is bjgreenberg/senior-engineering-partner's own configuration. It tells Claude Code how to work on senior-engineering-partner itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything senior-engineering-partner configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bjgreenberg/senior-engineering-partner. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bjgreenberg/senior-engineering-partner/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/bjgreenberg/senior-engineering-partner

Made for: Claude Code.

Wrote 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.

agentmods badge for senior-engineering-partner CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/bjgreenberg/senior-engineering-partner/claude-md/github.svg)](https://agentmods.dev/instructions/bjgreenberg/senior-engineering-partner/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/bjgreenberg/senior-engineering-partner/claude-md"><img src="https://agentmods.dev/badge/instructions/bjgreenberg/senior-engineering-partner/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.

agentmods 80×15 button for senior-engineering-partner CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/bjgreenberg/senior-engineering-partner/claude-md"><img src="https://agentmods.dev/badge/instructions/bjgreenberg/senior-engineering-partner/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,066 This file is loaded in full into every session.
When invoked 1,066 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01066 $0.01066
Opus 5.5 $0.00426 $0.00426
Sonnet 5.5 $0.00213 $0.00213
Haiku 4.5 $0.00107 $0.00107

Measured 21d ago against content hash 806e66962091, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

senior-engineering-partner 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 21d 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.

CLAUDE.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — senior-engineering-partner

Agent/contributor guide for working on this repo (the skill itself lives in SKILL.md + references/). Human-facing process docs: CONTRIBUTING.md and MAINTAINERS.md — this file is the agent-facing distillation.

Writer and reviewer (read before editing anything)

One model writes a change, and a different reader reviews it before the PR. Reading, auditing, and proposing changes are fine on any model. Writing to SKILL.md, references/, scripts/, evals/, or the repo docs is done by one writer per change; before the PR opens, a second reader — another model, or a human — reads the diff for unverified paths, flags, and commands; dense prose; and overreach past the evidence. The PR body records who wrote, who reviewed, and the reviewer's verdict. Any model may be the writer; this file names none. A private environment profile (references/my-environment.md) MAY name a writer, a reviewer, and the fallback for when the writer is unavailable; when it does, sessions in that environment follow it. Skipping the second read, or departing from a profile's named models, takes an express, per-change instruction from the maintainer; a general "go ahead" earlier in the session is not one. Rationale: one writer per change keeps its voice, judgment, and rule-wording consistent instead of a patchwork of whichever models were loaded, and a second reader catches what the writer misses.

Repo shape

  • SKILL.md — the universal core; references/ — deep-dive references loaded on demand; scripts/ — lint/guard/test tooling; evals/ — the eval harness (scenarios, fixtures, baselines).
  • The repo is PUBLIC. Environment-specific values bind through references/my-environment.md, which is .gitignored and never committed — the repo ships only references/my-environment.template.md. Never commit private identifiers (employers, hosts, domains, real names beyond the author) into code, commits, PR text, or eval baselines — the CI denylist is only a partial guard, not a substitute for care.
  • Cite only this repo. An issue, PR, or file named in a tracked file is one of this repo's own. Never name another repository, product, or an issue number from outside the skill; tell an origin incident generically (what happened, what it cost, why the existing rules missed it). Commit messages and PR bodies are public too, and the leakage guard does not scan them — the rule holds there by care alone.

Read the full file on GitHub · 81 lines

Changes

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.

  1. 21d ago Changed · +12 lines · +200 tokens per session 806e66962091
  2. 1mo ago First seen · 69 lines · 866 tokens per session scan A 66e49a5c8807

Subscribe to this mod's changes

senior-engineering-partner CLAUDE.md is an instructions file published in the GitHub repository bjgreenberg/senior-engineering-partner (154 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,066 tokens to every session, about $0.0043 per session on Opus 5.5. 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 2026-08-30.

Related

Other instructions, from other repositories