What is claude-coach CLAUDE.md?

A set of instructions and tools for coaching developers during and after coding sessions with Claude Code.

Use it for statusline tips, live session advice, frustration prompts, and post-session reflection processing.

It helps surface frustration, provide session advice, and turn completed-session signals into reflections while preserving required operating rules.

How kam-l/claude-coach configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to kam-l/claude-coach. 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/kam-l/claude-coach/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/kam-l/claude-coach

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/kam-l/claude-coach/claude-md/github.svg)](https://agentmods.dev/instructions/kam-l/claude-coach/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/kam-l/claude-coach/claude-md"><img src="https://agentmods.dev/badge/instructions/kam-l/claude-coach/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/kam-l/claude-coach/claude-md"><img src="https://agentmods.dev/badge/instructions/kam-l/claude-coach/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 988 This file is loaded in full into every session.

When invoked 988 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.

Model	Per session	Once invoked
Fable 5.1	$0.00988	$0.00988
Opus 5	$0.00494	$0.00494
Sonnet 5	$0.00198	$0.00198
Haiku 4.5	$0.00099	$0.00099

Measured 9d ago against content hash ec9928e3f1f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

claude-coach 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 9d 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 · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

claude-coach

Session-aware coaching — curated spinner tips, live Sonnet advisor, frustration coaching, session reflection.

Key Invariants

session-advisor.js is dual-mode (library + worker). Both must work after edits.
session-advisor.js MUST fallback CLAUDE_PLUGIN_DATA to ~/.claude/plugins/claude-coach/ — library mode callers (custom statusline) don't have the env var
Worker calls claude -p --model sonnet — correct claude -p usage (standalone, no Claude Code context)
reflect-pipeline.js calls claude -p --model sonnet once — runs detached after session ends
Reflection pipeline: SessionEnd hook → single Sonnet call (extract signals + generate reflections) → pending JSONL
Pending reflections: ~/.claude/projects/{slug}/pending-reflections.jsonl — append-only, per-project, cleared by /reflect
prompt-enrichment.js is frustration-only (local regex, no API calls, zero latency) — injects inline coaching, does NOT route to external commands
Advisor NEVER suggests /compact or /clear for context management — /clear is fine for topic changes or repeated-correction recovery
Statusline prefix: 💡 = random tip, ℹ️ = advisor display, ⚠️ = advisor inject, 🔍 = analyzing, 💭 = pending reflections
Statusline tip priority: ⚠️ inject-strength advice > 💭 pending reflections (always first if >0) > ℹ️ display-strength advice > 💡 random tip
install-statusline.js ensures mutable runtime dir exists, cleans stale copies — --wire detects existing statusline and generates a universal aggregator wrapper (forks stdin to original command, appends coach output) at ${CLAUDE_PLUGIN_DATA}/statusline-aggregator.js
Data files (tips.json, references/claude-usage.md) are read from the bundle (__dirname) — never copied to runtime
Mutable data (cache, logs, setup-context, pending-reflections) lives under ${CLAUDE_PLUGIN_DATA}
Env vars: CLAUDE_COACH (enable advisor), CLAUDE_COACH_INTERVAL (minutes, default 5), CLAUDE_COACH_COSTS (show cost in statusline)
Env vars: CLAUDE_COACH_DEBUG (enable debug logging to ${CLAUDE_PLUGIN_DATA}/reflect-debug.log)
Plugin is self-reliant — no dependencies on global-scope agents or commands

Read the full file on GitHub · 53 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.

9d ago First seen · 53 lines · 988 tokens per session scan A ec9928e3f1f7

Subscribe to this mod's changes

claude-coach CLAUDE.md is an instructions file published in the GitHub repository kam-l/claude-coach (11 stars, last pushed 5mo ago), licensed MIT. It adds 988 tokens to every session, about $0.0049 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 2026-08-30.

Productivity

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

claude-coach: Instructions file for Claude Code