What is BEST-Self-Enhancement-Learning-AI CLAUDE.md?

A session handoff file for BEST-Self-Enhancement-Learning-AI that records where project rules live, how related coding tools are configured, and what was completed in the previous session.

It helps agents locate the main instructions, resume ongoing work, understand the repository’s adapters and workflow, and review recent fixes and remaining tasks.

It gives a new coding session the context needed to continue work without changing copied configuration files or repeating finished investigations.

How subkoks/BEST-Self-Enhancement-Learning-AI configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to subkoks/BEST-Self-Enhancement-Learning-AI. 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/subkoks/BEST-Self-Enhancement-Learning-AI/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/subkoks/BEST-Self-Enhancement-Learning-AI

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/subkoks/best-self-enhancement-learning-ai/claude-md/github.svg)](https://agentmods.dev/instructions/subkoks/best-self-enhancement-learning-ai/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/subkoks/best-self-enhancement-learning-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/subkoks/best-self-enhancement-learning-ai/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/subkoks/best-self-enhancement-learning-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/subkoks/best-self-enhancement-learning-ai/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 5,742 This file is loaded in full into every session.

When invoked 5,742 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	$0.05742	$0.05742
Opus 5	$0.02871	$0.02871
Sonnet 5	$0.01148	$0.01148
Haiku 4.5	$0.00574	$0.00574

Measured 12d ago against content hash b551c0808c61, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

BEST-Self-Enhancement-Learning-AI 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 12d 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 · 276 lines

How it starts

The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BSELA — Claude Code entry

Canonical project rules live in AGENTS.md. Personal overlay: ~/AGENTS.md.

Rule changes belong in ~/Projects/Current/Active/agents-md, not in editor-synced copies under ~/.claude/.

Claude Code setup (Stop hook, MCP, repo permissions): see adapters/claude/README.md.

Multi-role dev workflow (optional): lead + focused sub-sessions use docs/orchestrator/ORCHESTRATOR.md and docs/orchestrator/README.md (ADR 0008; Agent SDK posture: 0009).

~~For Cursor (MCP wiring), see adapters/cursor/README.md~~ — Cursor retired 2026-06-17; adapter preserved as reference in adapters/README.md.

For Codex CLI continuation from this repo, see CODEX.md.

Last session — 2026-06-20 (agent-def review + security pins + capture dedup; 3 lessons applied)

Completed

Agent definitions reviewed & fixed (PRs #91–#93) — medium-effort code review of the 4 .claude/agents/*.md files from #90 surfaced 7 findings, all addressed: agent check commands now use make cov / make mcp-check (were uv run pytest -q / cd mcp && pnpm check, which skipped the coverage gate and left dist/server.js stale); removed unrecognized memory: frontmatter (Claude Code silently ignores it); hard-coded absolute path → repo-relative; .gitignore agent allowlist deepened to **.
Security pins (PRs #93, #96) — pinned vite 7.3.5 (exact; range syntax didn't resolve) + esbuild ≥0.28.1, bumped hono ≥4.12.25 (Dependabot #19–#23). Migrated all pnpm overrides from mcp/package.json (pnpm 10 ignores pnpm.overrides there with a WARN) → new mcp/pnpm-workspace.yaml. 0 open Dependabot alerts.
Capture dedup + scrubber allowlist (PR #95, closes #94) — root-caused an inflated quarantine rate: the Stop hook re-ingested the same growing transcript on every tool completion (~9.3× inflation; all unique quarantines were false positives on placeholder AWS keys). Fixes: transcript-path dedup in ingest_file (find_session_by_transcript, transcript_path indexed); a scrubber allowlist in config/thresholds.toml for known-safe doc/placeholder keys (scan() now uses finditer + per-match allowlist — pattern suppressed only when ALL matches are allowlisted). Branch count kept under PLR0912 via _make_result / _dedup_check helpers. New session captures land at ~2.1%.
Dogfood batch — bsela process --limit 20 --since-days 14: distilled 20, 4 new lessons (deduped against corpus), $0 free tier, no 429.
3 proposed lessons → applied — the v0.1.1 trio (809875ce declare/install Python deps; 6a6601cb no hard-coded absolute paths; 55adbcb3 retry+backoff on 429). Their drafts were already merged into agents-md main on 2026-06-07 (PR #31, drafts/bsela-lessons/); only the BSELA store was stale. Reconciled proposed → applied (note: "merged via PR #31"). Review queue now has 0 proposed.

Read the full file on GitHub · 276 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.

12d ago First seen · 276 lines · 5,742 tokens per session scan A b551c0808c61

Subscribe to this mod's changes

BEST-Self-Enhancement-Learning-AI CLAUDE.md is an instructions file published in the GitHub repository subkoks/BEST-Self-Enhancement-Learning-AI (2 stars, last pushed 4d ago), licensed MIT. It adds 5,742 tokens to every session, about $0.0287 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.

LLM Python ai-agents developer-tools mcp self-improvement

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.

github/spec-kit · 7,126 tokens

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

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

BEST-Self-Enhancement-Learning-AI: Instructions file for Claude Code