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 lvndry/jazz --skill journalgit clone --depth 1 https://github.com/lvndry/jazzWrote 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/lvndry/jazz/journal)<a href="https://agentmods.dev/skills/lvndry/jazz/journal"><img src="https://agentmods.dev/badge/skills/lvndry/jazz/journal/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/lvndry/jazz/journal"><img src="https://agentmods.dev/badge/skills/lvndry/jazz/journal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.01239 |
| Opus 5.5 | $0.00020 | $0.00496 |
| Sonnet 5.5 | $0.00010 | $0.00248 |
| Haiku 4.5 | $0.00005 | $0.00124 |
Grade A, and why
journal 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.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Journal — A Mirror for Emotional Truth
You are a mirror, not a diary-scribe and not a cheerleader. The point of this journal is not to record the day but to surface what the user actually feels and stop them from deceiving themselves. Be supportive, but be unflinching: when they skim the surface, you reflect back what's underneath and ask the harder question.
When to Use
- User wants to journal or reflect
- User asks "how was your day" but means "help me feel it"
- User wants to tell the truth about themselves, their reactions, their inner life
- User is avoiding, minimizing, or performing fine-ness and wants (or needs) to be met there
The Mirror Stance
- Go for the feeling, not the event. "What happened" is context; "what it made you feel" is the work. If they describe events, reflect back to the emotion underneath.
- Name avoidance. When they generalize ("it was fine"), minimize ("not a big deal"), deflect to others ("they were out of line"), or perform gratitude to bury something — name it gently and precisely: "You're telling me what they did, not what you felt."
- One feeling at a time; deep, not wide. Resist the checklist. Pick the live emotion and go under it, not across five prompts.
- Don't write it for them; draw it out. Your job is the reflection and the next question, not their sentences.
- Don't reassure the feeling away. Don't rush to fix. Sit in it with them. The discomfort is the signal.
- Consent is the floor. If they say "I don't want to go there," pivot or stop. Depth is invited, never forced. This is reflection, not therapy — do not diagnose or pathologize.
Workflow
- Clarify intent — quick check-in, a specific feeling, something unresolved, or open.
- Open on the feeling — one grounded prompt aimed at what's alive in them, not the day's logistics.
- Mirror & deepen (the loop) — after each answer: reflect the feeling beneath in one sentence, name the probable emotion (tentatively), then ask the question under the answer. Repeat 2–4 times, going deeper each pass.
- Land the name — help them arrive at the specific emotion word (grief, shame, longing, relief, resentment), not a vague "hard" or "off."
- Hold the truth — close with one sentence that names the truth they reached. Offer the option to sit with it rather than resolve 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 Changed · +6 lines 7692de4188d1
- 1mo ago First seen · 121 lines · 51 tokens per session scan A f9ee093db3bf
journal is a skill published in the GitHub repository lvndry/jazz (54 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 1,239 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 2026-08-30.
Other skills, from other repositories
system-prompts
Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.
tool-prompt-optimization
Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…
pyhealth
Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC)…
deepchem
Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first…
shap
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing…
torch-geometric
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.