A command that extracts lessons from the current coding session and saves them to a wiki. It looks for mistakes and fixes, user corrections, and useful discoveries.

Use it after a task to record structured lessons in the configured wiki, either locally or in the selected wiki.

It preserves practical knowledge from the session so the same problems and solutions can be found later.

ll — Command by nvk

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.

agentmods

npx agentmods add commands/nvk/llm-wiki/ll

Clone the repo

git clone --depth 1 https://github.com/nvk/llm-wiki

Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,398 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00031	$0.02398
Opus 5	$0.00015	$0.01199
Sonnet 5	$0.00006	$0.00480
Haiku 4.5	$0.00003	$0.00240

Measured 2d ago against content hash 2f4e540fe3fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ll 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 2d 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-plugin/commands/ll.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Your task

Resolve the wiki. Do NOT search the filesystem or read reference files — follow these steps:

Read $HOME/.config/llm-wiki/config.json. If it has hub_path, expand leading ~ only (not tildes in com~apple~CloudDocs) and prefer that path; use resolved_path only as a fallback cache when the expanded hub_path is unavailable and resolved_path is initialized. If config has only resolved_path, use it. If the configured path can be statted but reading wikis.json or listing topics/ fails with Operation not permitted, stop and ask the user to grant Full Disk Access/iCloud Drive access to the launcher; do not fall back to ~/wiki or resolved_path. Do not write machine-specific resolved_path into shared configs.
If no config → read $HOME/wiki/_index.md. If it exists → HUB = $HOME/wiki. If nothing found, ask the user where to create the wiki.
Wiki location (first match): --local → .wiki/ in CWD; --wiki <name> → HUB/wikis.json lookup with portable path resolution (<HUB>, ~, absolute, or HUB-relative); if the registry path is stale, fall back to HUB/topics/<name>; CWD has .wiki/ → use it; else → HUB.
Read <wiki>/_index.md to verify. If missing and no wiki matches the session topic → offer to create one with --new-topic; otherwise target the most relevant existing wiki.

Archive rule: lessons learned go to active topic wikis by default. Skip archived topics when auto-targeting by session topic. If --wiki <name> resolves to an archived topic, stop and ask the user to restore it or rerun with --include-archived; explicit archived writes must stay inside the archived topic path and keep it archived.

Extract lessons learned from the current session and save them to the wiki's knowledge pipeline.

Inventory awareness: if a lesson implies a durable follow-up, recurring watch item, or source/corpus candidate, suggest an inventory record in addition to the raw lesson note. Do not turn every lesson into inventory; only use it when there is status, priority, or a next action to track.

Read the full file on GitHub · 227 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.

2d ago First seen · 227 lines · 31 tokens per session scan A 2f4e540fe3fe

Subscribe to this mod's changes

ll is a command published in the GitHub repository nvk/llm-wiki (1,175 stars, last pushed 5d ago), licensed MIT. It adds 31 tokens to every session and 2,398 once invoked, about $0.0002 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.

Data and AI LLM Learning and teaching Planning agentic-ai agentic-skills agentic-workflow claude-code codex

ll

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Your task

What this file has done since we first saw it

Other commands, from other repositories

session-memory

implement

workflow-claude-commands

review

research-verify

test-feature