Borrowing it
Nothing to install: this file belongs to egorus1/ask-a-senior. 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/egorus1/ask-a-senior/master/CLAUDE.mdgit clone --depth 1 https://github.com/egorus1/ask-a-seniorWrote 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/egorus1/ask-a-senior/claude-md)<a href="https://agentmods.dev/instructions/egorus1/ask-a-senior/claude-md"><img src="https://agentmods.dev/badge/instructions/egorus1/ask-a-senior/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 5.1 | $0.01121 | $0.01121 |
| Opus 5 | $0.00561 | $0.00561 |
| Sonnet 5 | $0.00224 | $0.00224 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade A, and why
ask-a-senior 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 8d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ask-a-senior
A Claude Code plugin that makes Claude behave like a busy senior engineer: it refuses badly-formed questions, answers good ones with a hint rather than a solution, and never writes your code.
The rule everything serves
The friction is the product. Anything that makes the plugin more eager to help makes it worse. When a change would smooth a rough edge, first ask whether that edge was the point. Most of them are.
The one thing being taught is not the bug in front of the user — it's how to ask a question that can be answered. That is why a refusal always names the single missing piece instead of saying "please provide more detail." A refusal that doesn't teach is just stonewalling.
Layout
skills/ask-a-senior/SKILL.md the doctrine — loaded once, when invoked
hooks/persona.js the compact version — injected every turn
hooks/prompt-submit.js command router + per-turn persona injection
hooks/guard.js PreToolUse deny on Edit/Write/MultiEdit/NotebookEdit
hooks/session-start.js re-arms a resumed or compacted session
hooks/statusline.js [senior · 12m · 4 asked] badge
hooks/lib.js session state, stdin plumbing
hooks/hooks.json hook registration (auto-discovered by this path)
commands/*.md /ask-a-senior:on|off|status|log|statusline
tests/hooks.test.js node --test tests/
plugin.json deliberately has no hooks key — Claude Code discovers
hooks/hooks.json by convention, and declaring it as well registers every hook
twice, which double-counts questions and writes two JSON objects to one stdout.
Why there are hooks at all
The model could in principle do all of this from SKILL.md. Each hook exists because a prompt provably can't hold the line:
- guard.js — "you will not get code back" is a promise a determined user can argue a model out of. A denied tool call is not arguable. This is what makes the tagline true rather than aspirational.
- prompt-submit.js — a persona stated once drifts back toward helpfulness over a long session, and is dropped outright at compaction. Re-injecting each turn is the fix. It also owns the question counter, because after a compact the model can't see its own earlier refusals and would restart the two-refusal budget on a problem it has already refused twice.
- session-start.js — resumed sessions would otherwise come back as a normal assistant with the file-edit block still armed.
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.
- 8d ago First seen · 103 lines · 1,121 tokens per session scan A 5052c03f33c2
ask-a-senior CLAUDE.md is an instructions file published in the GitHub repository egorus1/ask-a-senior (2 stars, last pushed 18d ago), licensed MIT. It adds 1,121 tokens to every session, about $0.0056 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
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.
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.
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).
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).
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.
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.