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/vshulcz/deja-vu/recallgit clone --depth 1 https://github.com/vshulcz/deja-vuWrote 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/vshulcz/deja-vu/recall)<a href="https://agentmods.dev/commands/vshulcz/deja-vu/recall"><img src="https://agentmods.dev/badge/commands/vshulcz/deja-vu/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 5.1 | $0.00017 | $0.00174 |
| Opus 5 | $0.00009 | $0.00087 |
| Sonnet 5 | $0.00003 | $0.00035 |
| Haiku 4.5 | $0.00002 | $0.00017 |
Grade A, and why
recall scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
97% identical to deja — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Search the user's own past sessions across every AI coding tool on this machine, then answer from what you find.
Run the recall tool with the user's words as the query — the most specific tokens win (an exact error string, a function name, a file path, a flag). If a result looks right but is too short to act on, follow up with recall_context using a term from it.
If the deja MCP tools are unavailable, fall back to the CLI:
deja search -- "$ARGUMENTS"
Answer with what actually happened in those sessions — when it was, which project and tool, what was decided or fixed. Say plainly if nothing matched rather than filling the gap from general knowledge.
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 Changed 5ddaca370f12
- 6d ago First seen · 23 lines · 17 tokens per session scan A a373941b43ef
recall is a command published in the GitHub repository vshulcz/deja-vu (776 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 174 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to deja, differing in 2 lines, and is treated as a copy.
Other commands, from other repositories
search
Complete reference for querying the global Jumbo memory search index.
tour
Tour this project's memory — what's captured, where it lives, how to recall it (core-memory-kit).
remember
Save something to long-term local memory.
recall
Search long-term local memory and answer from it.
load
Load the shared Wingman context for this project.
krimto-status
Show the current state of Krimto memory — total facts, scope breakdown, recent writes, and index health.