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 techygarg/lattice --skill learning-harvestgit clone --depth 1 https://github.com/techygarg/latticeWrote 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/techygarg/lattice/learning-harvest)<a href="https://agentmods.dev/skills/techygarg/lattice/learning-harvest"><img src="https://agentmods.dev/badge/skills/techygarg/lattice/learning-harvest.svg" alt="Measured on agentmods" 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 | $0.00114 | $0.02142 |
| Opus 5 | $0.00057 | $0.01071 |
| Sonnet 5 | $0.00023 | $0.00428 |
| Haiku 4.5 | $0.00011 | $0.00214 |
Grade A, and why
learning-harvest 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 8d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learning Harvest
Scope Boundary
Operational learnings are NOT rules. They are what you learn while applying rules.
| Standards (refiner output, atom defaults) | Operational Learnings (this document) |
|---|---|
| "Domain layer must not import from infrastructure" | "When adding a new aggregate, we keep forgetting to define the repository interface first — design interface before implementation" |
| "Functions should have single responsibility" | "Service classes that start small grow past 500 lines within 3 features — split by command type proactively at ~200 lines" |
| "Value objects must validate in constructor" | "Date range VOs without explicit inclusive/exclusive documentation cause boundary bugs every time — document semantics alongside validation" |
The standard is the rule. The operational learning is what we discovered while applying the rule on this project.
If an entry reads like a rule that should always be followed, it belongs in a standards document (run the relevant refiner). If it reads like "here's what we keep learning the hard way" or "here's an approach that keeps working for us" — it belongs here.
Patterns that recur frequently may graduate to standards via a refiner. That promotion path is part of the Tighten behavior.
Config Resolution
- Check
.lattice/config.yamlforpaths.operational_learnings. - If set and the file exists at that path → use it.
- If set but no file exists there → tell the user which configured path is missing, then use the default
.lattice/learnings/operational-learnings.md. - If not set → use the default
.lattice/learnings/operational-learnings.md.
Backward compatibility: If default path not found, check these legacy paths in order:
.lattice/learnings.md— flat file at root.lattice/learnings/review-insights.md— prior naming convention
If found, offer migration to canonical path and format. If user declines, read as flat input. STOP: do not write to it.
Document Structure
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.
- 8d ago First seen · 165 lines · 114 tokens per session scan A fd6609fa23af
learning-harvest is a skill published in the GitHub repository techygarg/lattice (185 stars, last pushed today), licensed MIT. It adds 114 tokens to every session and 2,142 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
recall
Recall prior work from past sessions — how a bug was fixed, what was decided, where a pattern lives. Use when asked 'have we done this before' or 'how did I fix X' in Elixir/Phoenix work. ccrider MCP when available, else git + solution docs.
assigns-audit
Inspect LiveView socket assigns for memory bloat — missing temporaryassigns, unused assigns, unbounded lists needing streams, memory estimates. Use when LiveView memory grows or you need to add temporaryassigns.
compound-docs
Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter. Builds institutional knowledge from solved problems. Use when consulting past solutions before investigating new issues.
name-your-business
Generate, refine, compare, and when needed validate distinctive names for startups, AI products, developer tools, protocols, open-source projects, apps, product families, local businesses, services, companies, nonprofits, and other organizations. Use when asked to name or rename a business, brand, product, venture…
top-one-percent
Teach any topic deeply from first principles and build evidence-based paths toward exceptional capability. Use when a user asks to understand, explain, learn, or deep-dive into a topic; asks why or how something works, why it matters, how alternatives compare, or what different perspectives reveal; requests current…