deja-vu is a local memory system that indexes coding-agent session histories and makes relevant past work available to other agents. It helps users share fixes and context across Claude Code, Codex, Cursor, Copilot CLI, and other coding agents without using a language model or embeddings. The catalogue contains hooks, commands, MCP components, skills, plugins, and instructions for connecting agents to that memory.
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 skills add vshulcz/deja-vu --skill deja-reflectgit 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/skills/vshulcz/deja-vu/deja-reflect)<a href="https://agentmods.dev/skills/vshulcz/deja-vu/deja-reflect"><img src="https://agentmods.dev/badge/skills/vshulcz/deja-vu/deja-reflect/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/skills/vshulcz/deja-vu/deja-reflect"><img src="https://agentmods.dev/badge/skills/vshulcz/deja-vu/deja-reflect.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 | $0.00049 | $0.00322 |
| Opus 5.5 | $0.00020 | $0.00129 |
| Sonnet 5.5 | $0.00010 | $0.00064 |
| Haiku 4.5 | $0.00005 | $0.00032 |
Grade A, and why
deja-reflect 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 yesterday.
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
Run an end-of-session reflection over the current task and record only durable, non-obvious project facts in deja-vu.
Workflow
- Inspect what was already recorded or hit in this project:
- Call the
dejatool withmode: "orient"(or rundeja notesanddeja frictionin the shell) to see existing promoted decisions and recurring walls so you do not duplicate an active note.
- Call the
- Distill durable findings from this session:
- Keep: architectural invariants, required flags/commands that were non-obvious, rejected approaches and why they failed, user-stated project rules.
- Skip: anything already obvious from reading the code, temporary debugging steps, or one-off typos.
- Confirm with the user before writing:
- Present the 1–3 concise one-line facts you propose to store.
- Once confirmed, call the
dejatool withmode: "remember"andquery: "<concise self-contained decision and why>"(or rundeja remember "<fact>"in the shell). - If an older note was superseded by today's work, run
deja promote <id> --state superseded --note "<what replaced it>".
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.
- yesterday First seen · 19 lines · 49 tokens per session scan A 261a2885fd87
deja-reflect is a skill published in the GitHub repository vshulcz/deja-vu (1,386 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 322 once invoked, about $0.0002 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 2026-11-03.
Other skills, from other repositories
help-flow
Help about Rosetta: explains capabilities and usage.
init-workspace-documentation
Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.
external-lib-flow
Workflow for onboarding an external private library so AI can use it without source access.
modernization-flow
Workflow for converting, modernizing, upgrading, or re-architecting code (e.g. C++→Java, monolith→microservices), etc.
identity-snapshot
Generate a living profile of the user's working patterns, decision tendencies and quality preferences from their Dex data. Use when the user says 'what are my patterns', 'how do I work', or during week-review. Also use proactively when the model (older than 7 days) is stale. Not for planning a week; use week-plan.
save-progress
Save current project task progress to local task state file for cross-session continuity. Use when the user asks to save progress, uses an equivalent localized trigger phrase, the session is interrupted, or the user wants to resume work later. Writes to .claude/project-task-state.json so next session can load it via…