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.
Borrowing it
Nothing to install: this file belongs to vshulcz/deja-vu. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vshulcz/deja-vu/main/.claude/commands/harness.mdgit 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/harness)<a href="https://agentmods.dev/commands/vshulcz/deja-vu/harness"><img src="https://agentmods.dev/badge/commands/vshulcz/deja-vu/harness/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/commands/vshulcz/deja-vu/harness"><img src="https://agentmods.dev/badge/commands/vshulcz/deja-vu/harness.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 | $0.00017 | $0.01521 |
| Opus 5.5 | $0.00007 | $0.00608 |
| Sonnet 5.5 | $0.00003 | $0.00304 |
| Haiku 4.5 | $0.00002 | $0.00152 |
Grade A, and why
harness 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.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/harness
<name> is one harness. deja sources lists every one deja reads and
deja install names the ones it can wire on this machine; those two lists are
the authority, not a copy of them here. With no argument, take the harness with
the most sessions in deja doctor that has not been through this recently.
What this is for
deja is not a CLI for a person to run. Its value is that an agent gets smarter without being asked: it starts a session already knowing what this machine settled, and it is reminded at the moment it is about to repeat a mistake. A harness is finished when that happens by itself, looks right on screen, and costs almost nothing.
Three things are being judged, in this order:
- Does the memory reach the model. Not "the hook is wired" — the bytes.
- Is it worth reading. A count is not a decision. "You have run this before" changes nothing; "last time this wiped the staging queue, and the flag that fixed it" changes the next tool call.
- What it costs. Latency on every action and tokens in every turn.
The bar
A harness is done when all of these are true and you have seen each one yourself, on this machine:
- Every channel the harness offers is wired: session start, per prompt, before
a tool runs, after one fails, on compaction, and whatever it calls spawning a
subagent.
deja doctorreports no row out of date. - The recall is in the request the harness actually sent, read out of the bytes, not inferred from the hook printing something.
- A question whose answer exists only in history is answered from history. Use an invented token — a real answer cannot be a guess.
- The slash command runs a search. It must not hand the query to deja as its first word, and it must survive a query that names one of deja's own flags.
- A second copy of the plugin, or a plugin whose peer is missing, degrades. It never takes the profile down.
- The output looks right where the user sees it — the TUI, the toast, the collapsed row. Render it and look at it.
- The cost is measured and stated: milliseconds per action, bytes per turn.
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 · -5 lines c35c9c3330a3
- 1mo ago First seen · 129 lines · 17 tokens per session scan A 8866db39e176
harness is a command published in the GitHub repository vshulcz/deja-vu (1,314 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 1,521 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
test
Design or run focused test validation for a task, bug, or diff.
ng-red-team
Portable command prompt generated from skills/stress-testing-agent-changes/SKILL.md. Edit the skill, then run python tools/ng.py gen-commands; do not edit this file by hand.
usage-add
PitWay: Accumulate measured planning or qa token usage onto a milestone.
regression-suite
Map test coverage to GDD critical paths.
test-setup
Scaffold test framework and CI pipeline.
recall
Recall durable project context for a concrete question.