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/tony/claude-code-riper-5/recallgit clone --depth 1 https://github.com/tony/claude-code-riper-5Wrote 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/tony/claude-code-riper-5/recall)<a href="https://agentmods.dev/commands/tony/claude-code-riper-5/recall"><img src="https://agentmods.dev/badge/commands/tony/claude-code-riper-5/recall.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 | $0.00008 | $0.00499 |
| Opus 5 | $0.00004 | $0.00249 |
| Sonnet 5 | $0.00002 | $0.00100 |
| Haiku 4.5 | $0.00001 | $0.00050 |
Grade B, and why
recall scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Memory-bank MUST be at repository root: Use `git rev-parse --show-toplevel` to find root, then `[ROOT]/.claude/memory-bank/` What it actually says
Recalling from Memory Bank
I'll retrieve memories from the branch-aware memory bank.
⚠️ Memory Bank Location Requirements
CRITICAL PATH POLICY:
- Memory-bank MUST be at repository root: Use
git rev-parse --show-toplevelto find root, then[ROOT]/.claude/memory-bank/ - NEVER create package-level memory-banks:
packages/*/.claude/memory-bank/❌ - In monorepos: ONE memory-bank at root serves entire project
Correct vs Incorrect Paths for Recall
✅ Correct: [ROOT]/.claude/memory-bank/main/session.md (where ROOT = git rev-parse --show-toplevel)
❌ Wrong: [ROOT]/packages/react/.claude/memory-bank/main/session.md
❌ Wrong: packages/react/.claude/memory-bank/main/session.md
Current Context
- Branch: !
git branch --show-current - Date: !
date +%Y-%m-%d
Git History Since Last Session
Show commits since last memory save:
last_memory=$(ls -t $(git rev-parse --show-toplevel)/.claude/memory-bank/$(git branch --show-current)/sessions/*.md 2>/dev/null | head -1)
if [ -n "$last_memory" ]; then
last_date=$(stat -c %y "$last_memory" | cut -d' ' -f1)
git log -n 10 --oneline --since="$last_date"
fi
Show recent changes to memory bank:
git log -n 5 -p -- .claude/memory-bank/
Search Scope
Looking for memories in: [ROOT]/.claude/memory-bank/!git branch --show-current/ (where ROOT = git rev-parse --show-toplevel)
Search Query
$ARGUMENTS
Available Memories
!ls -la $(git rev-parse --show-toplevel)/.claude/memory-bank/$(git branch --show-current)/ 2>/dev/null || echo "No memories found for current branch"
I'll search for and display relevant memories based on your query, along with git history context since the last session.
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.
- 5d ago First seen · 50 lines · 8 tokens per session scan B d34f28e6fdb9
recall is a command published in the GitHub repository tony/claude-code-riper-5 (93 stars, last pushed 19d ago), licensed MIT. It adds 8 tokens to every session and 499 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
cleanup-context
You are a memory bank optimization specialist tasked with reducing token usage in the project's documentation system while maintaining all essential information and improving organization.
update-memory-bank
Can you update CLAUDE.md and memory bank files.
dream
Memory consolidation — dedupe, contradiction-check, prune, and re-rank MEMORY.md + CLAUDE.md Project Learnings. Run after major refactors.
setup
First-run setup — pick a compact-manager mode and learn the commands.
init
从零开始 — 触发 dask-CS 跑需求澄清与架构决策，产出 decision-log.
plan
技术规范 — 文件路径、函数签名、变更规格、架构概览、编号清单.