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.
git clone --depth 1 https://github.com/runnithan/claudex-setupWrote 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/commands/runnithan/claudex-setup/extract-lessons)<a href="https://agentmods.dev/commands/runnithan/claudex-setup/extract-lessons"><img src="https://agentmods.dev/badge/commands/runnithan/claudex-setup/extract-lessons/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.
<a href="https://agentmods.dev/commands/runnithan/claudex-setup/extract-lessons"><img src="https://agentmods.dev/badge/commands/runnithan/claudex-setup/extract-lessons.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00029 | $0.06411 |
| Opus 5.5 | $0.00012 | $0.02564 |
| Sonnet 5.5 | $0.00006 | $0.01282 |
| Haiku 4.5 | $0.00003 | $0.00641 |
Grade A, and why
extract-lessons 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 today.
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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extract Lessons
Mine reusable agent-tooling lessons from locally saved practitioner transcripts and file each one into the lessons/ library as its own markdown file, keeping lessons/INDEX.md and the processed-transcript ledger in sync. Newer lessons supersede older contradicting ones on the same topic.
A "lesson" is a concrete, transferable improvement to how someone uses the agent tooling this repo tracks, Claude Code, Claude Design, or Codex: a command, flag, hook, skill pattern, workflow, config, design-surface technique, or gotcha that a reader could apply. Marketing claims, hype, product announcements without a usable technique, and generic AI-coding platitudes are NOT lessons.
Scope covers all three tools, do not silently drop two of them. This command was Claude-Code-only until 2026-07-17, and the omission was self-confirming: Claude Design and Codex transcripts were marked processed while yielding ~0 lessons, so
/optimise --designand--codexkept concluding "no relevant lessons exist" when the truth was that nobody had ever looked. A 28k-word Claude Design course and a 1-hour Codex course both extracted zero. If a transcript teaches real Claude Design or Codex technique, that is in scope and must be filed underdesignorcodex. A zero-lesson result for a technique-dense transcript is a red flag to re-read it, not a valid outcome.
Arguments
$ARGUMENTS:
- empty or
new(default): process only transcripts not yet inlessons/.processed.json all: reprocess every transcript (rare, only when the extraction criteria change). The criteria changed on 2026-07-17 (scope widened to Claude Design + Codex), so every transcript ledgered before that date was mined against Claude-Code-only criteria and its.processed.jsonentry is not evidence that its design or Codex content was ever considered. Re-run withallover the design/Codex-heavy scopes to backfill. They changed again on 2026-08-29 (one atomic claim per lesson), so a transcript ledgered before that date is not evidence its granular sub-tips were ever extracted: the 2026-08-31 consolidation split pass recovered only what compound lessons already carried as clauses, not what miners never wrote. Backfill withallover targeted scopes, starting with transcripts whose lessons needed splitting.- a path or glob (e.g.
transcripts/ray-amjad/): process just that scope, minus already-processed (unlessallis also passed)
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.
- today Changed · +1 lines 2d8285a3fc67
- 26d ago Changed · +6 lines 19cf57effcf6
- 1mo ago Changed · +11 lines 869fbbebd73b
- 1mo ago Changed 13735d9d0dc2
- 1mo ago First seen · 235 lines · 29 tokens per session scan A 3db34034dc4a
extract-lessons is a command published in the GitHub repository runnithan/claudex-setup (1 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 6,411 once invoked, about $0.0001 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.
Other commands, from other repositories
recall-save
Generate / overwrite .recall/context.md with Recall's local offline summarizer.
update-counts
Explicitly refresh public toolkit and committed marketplace source snapshots and numeric documentation.
security-review
A security review procedure based on CWE, a list of common software weaknesses, and STRIDE, a method for identifying threats to a system.
notebook-query
Query the notebook knowledge base (SQLite) built by /agy:notebook — precise, grounded, cited. Ask in natural language ("sum the amounts by category", "which docs mention 'Acme Corp'", "build a project timeline") or pass raw SQL. Read-only. Use this when you need exact aggregates/lookups across a document corpus…
refactor
Analyze code for SOLID violations and suggest targeted improvements.
generate-tests
Generate comprehensive tests for specified code.