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.
npx agentmods add commands/andiupn/andy-universal-agent-rules/save-from-chatgit clone --depth 1 https://github.com/andiupn/andy-universal-agent-rulesWrote 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/andiupn/andy-universal-agent-rules/save-from-chat)<a href="https://agentmods.dev/commands/andiupn/andy-universal-agent-rules/save-from-chat"><img src="https://agentmods.dev/badge/commands/andiupn/andy-universal-agent-rules/save-from-chat.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00294 |
| Opus 5 | $0.00000 | $0.00147 |
| Sonnet 5 | $0.00000 | $0.00059 |
| Haiku 4.5 | $0.00000 | $0.00029 |
Grade A, and why
save-from-chat 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 4d 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.
What it actually says
Save Knowledge from Chat
Scan this chat session and save important learnings to the knowledge base.
What to Look For
- ❌ Errors that occurred and their solutions
- ✅ Solutions that worked
- 💡 Patterns or techniques that were effective
- 🏗️ Decisions about architecture or technology
- ⚠️ Gotchas to avoid in the future
Categories
| Category | Use When |
|---|---|
gotchas |
Production bugs, errors to avoid |
patterns |
Working code patterns |
decisions |
Architecture/tech choices |
context |
Project information |
How to Save
# Save a gotcha
python .agent/scripts/save-knowledge.py --category gotchas "CRITICAL: describe the issue and solution"
# Save a pattern
python .agent/scripts/save-knowledge.py --category patterns "PATTERN: describe the pattern"
# Save a decision
python .agent/scripts/save-knowledge.py --category decisions "DECISION: what was decided and why"
Expected Output
Report what was saved:
✅ Saved 3 learnings from this chat:
- gotchas/issue-name.md
- patterns/pattern-name.md
- decisions/decision-name.md
Use: Type /save-from-chat in Cursor Chat
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.
- 4d ago First seen · 49 lines · 0 tokens per session scan A 698d8d73ae05
save-from-chat is a command published in the GitHub repository andiupn/andy-universal-agent-rules (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 294 tokens. 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
explore-problem
Analyze an issue through five lenses and post a Functional Specification.
acceptance-tests-prompts-commands
Command "acceptance-tests-prompts-commands" from jabrena/plinth, covering acceptance test prompts for commands, /onboarding, /benchmark, /create-acceptance-criteria and /create-adr.
benchmark
Design and coordinate a reproducible Java performance test.
profile
Coordinate a reproducible Java profiling and optimization lifecycle.
update-issue
Update an issue description with structured, evidence-backed content.
create-diagram
Create an architecture or design diagram from selected source artifacts.