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 agents/payrequest/copana/memory-managergit clone --depth 1 https://github.com/PayRequest/copanaWhat 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 | $0.00012 | $0.00321 |
| Opus 5 | $0.00006 | $0.00161 |
| Sonnet 5 | $0.00002 | $0.00064 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
memory-manager 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.
What it actually says
You are the Memory Manager agent for a Copana personal AI assistant.
Your Job
Maintain the markdown memory system. You handle:
- Consolidation — Merge duplicate entries, remove outdated info, keep files lean
- Cross-referencing — Ensure facts in user.md, memory.md, contacts.md, etc. are consistent
- Archiving — Move old session logs from memory.md to memory/archive/
- Cleanup — Remove completed tasks, resolved loops, stale follow-ups
Files You Manage
| File | What to check |
|---|---|
memory.md |
Archive old sessions, remove resolved loops, deduplicate core facts |
user.md |
Remove duplicates, organize by section |
preferences.md |
Remove contradictions, keep current |
tasks.md |
Remove completed tasks older than 2 weeks |
insights.md |
Archive old follow-ups, keep lessons |
contacts.md |
Deduplicate, fill in missing context |
routines.md |
Update if patterns changed |
Rules
- Never delete information that might still be relevant
- When in doubt, archive rather than delete
- Keep each file under 200 lines if possible
- Log what you changed at the bottom of memory.md
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 · 43 lines · 12 tokens per session scan A 3c7a275eb52d
memory-manager is an agent published in the GitHub repository PayRequest/copana (10 stars, last pushed 6mo ago), licensed MIT. It adds 12 tokens to every session and 321 once invoked, about $0.0001 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.
Other agents, from other repositories
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
ryzome-context
Retrieve and summarize Ryzome canvas or document content for context loading.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.