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 PSkinnerTech/brainlift-writer-skill --skill brainlift-writergit clone --depth 1 https://github.com/PSkinnerTech/brainlift-writer-skillWrote 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/pskinnertech/brainlift-writer-skill/brainlift-writer)<a href="https://agentmods.dev/skills/pskinnertech/brainlift-writer-skill/brainlift-writer"><img src="https://agentmods.dev/badge/skills/pskinnertech/brainlift-writer-skill/brainlift-writer/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/pskinnertech/brainlift-writer-skill/brainlift-writer"><img src="https://agentmods.dev/badge/skills/pskinnertech/brainlift-writer-skill/brainlift-writer.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 | $0.00098 | $0.01049 |
| Opus 5 | $0.00049 | $0.00524 |
| Sonnet 5 | $0.00020 | $0.00210 |
| Haiku 4.5 | $0.00010 | $0.00105 |
Grade A, and why
brainlift-writer 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 11d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BrainLift Writer
Overview
Create BrainLifts as portable context documents for any AI model. Treat a BrainLift as a structured record of human thinking: raw knowledge becomes summaries, summaries become insights, and insights become strong, defensible points of view.
Read references/brainlift-template.md when drafting a full BrainLift from scratch, converting a large note dump, or auditing section-level completeness.
Core Workflow
-
Establish the purpose.
- Write one concise North Star that names the central question, mission, or belief.
- Add
In ScopeandOut of Scopeboundaries to prevent drift. - Keep the BrainLift focused on what the author wants to understand, decide, teach, or repeatedly hand to AI.
-
Build the foundation before forcing conclusions.
- Extract DOK 1 facts from sources as objective claims.
- Summarize those facts into DOK 2 knowledge using the author's own words.
- Group knowledge into a hierarchy of categories, subcategories, and sources.
-
Synthesize DOK 3 insights.
- Turn organized knowledge into original conclusions, patterns, tensions, or connections.
- Make each insight a complete thought, not a source summary.
- Group insights thematically so they can support higher-level arguments.
-
Form DOK 4 spiky points of view.
- State each SPOV as a strong, clear assertion.
- Defend it by combining multiple DOK 3 insights, especially from different sources or domains.
- Explain implications, tradeoffs, and why the stance is not a generic AI-generated take.
-
Add experts.
- Include the people, labs, companies, books, papers, or communities the author should keep following.
- For each expert, capture who they are, what they focus on, why they matter to this BrainLift, and where to find their work.
-
Assemble in BrainLift order.
OwnersPurposeIn ScopeOut of ScopeDOK 4: Spiky Points of ViewExpertsDOK 3: InsightsDOK 2: Knowledge Tree
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 100 lines · 98 tokens per session scan A 5352405dac9f
brainlift-writer is a skill published in the GitHub repository PSkinnerTech/brainlift-writer-skill (8 stars, last pushed 2mo ago), licensed MIT. It adds 98 tokens to every session and 1,049 once invoked, about $0.0005 per session on Opus 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 2026-08-31.
Other skills, from other repositories
weights-and-biases
W&B: log ML experiments, sweeps, model registry, dashboards.
flash-attention
Speed up long-sequence transformer training and inference.
nemo-curator
Curate LLM training data: dedupe, filter, PII redaction.
stable-diffusion
Text-to-image generation, inpainting, and img2img.
chroma
Embedding database for RAG and semantic search.
pinecone
Managed vector DB for production RAG and search.