A team-knowledge skill that turns a coding rule or lesson into a shared CLAUDE.md instruction or a rule file under .claude/rules/. CLAUDE.md files give coding agents project-specific guidance.

Use it to record project conventions, debugging lessons, guard rails, and mechanically enforceable practices as shared agent instructions.

It preserves lessons from reviews, debugging, and incidents so the whole team can apply them in later sessions instead of repeating the same mistake.

bp-learn — Skill for Claude Code by kulmam92

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add kulmam92/cc-best-practices-marketplace --skill bp-learn

Clone the repo

git clone --depth 1 https://github.com/kulmam92/cc-best-practices-marketplace

Made for: Claude Code.

Or install cc-best-practices, the plugin that ships this one along with the rest of its 6 skills, 1 hook.

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/skills/kulmam92/cc-best-practices-marketplace/bp-learn/github.svg)](https://agentmods.dev/skills/kulmam92/cc-best-practices-marketplace/bp-learn)

Your own site

<a href="https://agentmods.dev/skills/kulmam92/cc-best-practices-marketplace/bp-learn"><img src="https://agentmods.dev/badge/skills/kulmam92/cc-best-practices-marketplace/bp-learn/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/skills/kulmam92/cc-best-practices-marketplace/bp-learn"><img src="https://agentmods.dev/badge/skills/kulmam92/cc-best-practices-marketplace/bp-learn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,132 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00067	$0.01132
Opus 5.5	$0.00027	$0.00453
Sonnet 5.5	$0.00013	$0.00226
Haiku 4.5	$0.00007	$0.00113

Measured 2mo ago against content hash 25e1dcd4f2c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bp-learn 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 2mo 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.

plugins/cc-best-practices/skills/bp-learn/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Team Rule Capture -- Compounding Engineering

Turn every code review, debugging session, and incident into a permanent team-wide improvement. This is Boris Cherny's "compounding engineering" -- every session benefits from all previous sessions' learnings.

Auto-memory handles personal learnings automatically. This skill is for team-shared rules committed to git so the whole team benefits.

Steps

Parse the rule from the provided arguments. Understand what convention, anti-pattern, or guard rail needs to be captured.

1b. Check correction context -- If this rule came from a correction or debugging session, mention Boris's golden rule: "After every correction, capture the lesson so it never happens again." If the pattern is mechanically enforceable (e.g., SQL conventions, import ordering, naming patterns), strongly suggest a lint rule (option c) -- enforcement always beats advice.

Detect scope -- is this rule project-wide or component-specific?
- Check if the project has multiple components (look for subdirectory CLAUDE.md files or common multi-component layouts like frontend/, backend/, infra/, packages/)
- If multi-component: ask "Is this rule for the whole project, or specific to [detected components]?"
- If single-component: skip -- it's project-wide
Auto-select output target based on project structure (do NOT ask):
- Single-component project → write to CLAUDE.md
- Multi-component project → write to .claude/rules/<topic>.md (project-wide) or .claude/rules/<component>-<topic>.md with paths frontmatter (component-specific)
- If CLAUDE.md is at ~150+ lines → automatically use .claude/rules/ instead and note why
- If a linter is detected and the pattern is mechanically enforceable → suggest a lint rule as well
- Mention graduation path inline: "This is an advisory rule. If it keeps recurring, graduate to a lint rule or hook via /bp-audit."
Only ask the user to choose a target if:
- The rule could reasonably go to multiple components
- The user explicitly requests a different target

Read the full file on GitHub · 83 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.

2mo ago First seen · 83 lines · 67 tokens per session scan A 25e1dcd4f2c6

Subscribe to this mod's changes

bp-learn is a skill published in the GitHub repository kulmam92/cc-best-practices-marketplace (2 stars, last pushed 7mo ago), licensed MIT. It adds 67 tokens to every session and 1,132 once invoked, about $0.0003 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 2026-08-31.

Memory and context

bp-learn next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
bp-learnkulmam92/cc-best-practices-marketplace	Skill	2	7mo ago	MIT	A	67	Claude Code
knowledge-ingestopenclaw/openclaw	Skill	394k	today	MIT	A	80	Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0	Skill	69k	today	Apache-2.0	A	217	Claude Code, Codex
forgetasgeirtj/system_prompts_leaks	Skill	71k	today	CC0-1.0	A	0	Claude Code, Codex
Cortexdanielmiessler/LifeOS	Skill	20k	yesterday	MIT	A	184	Claude Code
memoryopensquilla/opensquilla	Skill	7.1k	6d ago	Apache-2.0	A	44	Claude Code, Codex
ha-data-storesshiwenwen/hope-agent	Skill	1.9k	today	MIT	A	115	Claude Code, Codex