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 agentmods add skills/techygarg/lattice/refiners-updatenpx skills add techygarg/lattice --skill refiners-updategit clone --depth 1 https://github.com/techygarg/latticeWhat 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 | $0.00115 | $0.02045 |
| Opus 5 | $0.00057 | $0.01022 |
| Sonnet 5 | $0.00023 | $0.00409 |
| Haiku 4.5 | $0.00012 | $0.00204 |
Grade A, and why
refiners-update 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 3d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refiners Update
The update-mode counterpart to lattice-init. Where lattice-init detects missing standards and routes you to refiners to create them, this molecule detects existing standards and routes you to each refiner's revise mode to update them after a significant change — then records what changed and why.
It orchestrates the refiners; it never reimplements their interviews. Versioning is git-native: history lives in commits, and each revised document gets a one-line change note. No version numbers are introduced.
Required Skills
Read, apply:
framework:knowledge-priming-- Load project context. Understand what the project is and how the code has drifted from the current standards (always).
What This Does (and does not)
- Does: coordinate revising one or more existing standards documents after a change, and append a change note to each.
- Does not: create standards that do not exist yet (that is
lattice-init+ the relevant refiner), reimplement any refiner's interview, or introduce version numbers.
If the change requires a standard that does not exist yet (e.g. the team just adopted DDD but there is no ddd-principles.md), that is creation — direct the user to /lattice-init or the relevant refiner to create it, and note it in the summary.
Refiner → standards document map
Standards doc (in .lattice/standards/) |
Refiner to revise it | Config key |
|---|---|---|
knowledge-base.md |
/knowledge-priming-refiner |
paths.knowledge_base |
language-idioms.md |
/language-idioms-refiner |
paths.language_idioms |
architecture.md |
/architecture-refiner |
paths.architecture |
ddd-principles.md |
/ddd-refiner |
paths.ddd_principles |
clean-code.md |
/clean-code-refiner |
paths.clean_code |
review-standards.md |
/review-refiner |
paths.review_standards |
requirement-standards.md |
/requirement-forge-refiner |
paths.requirement_standards |
Maintainer note: This table mirrors the refiner inventory. When a refiner is added or removed, update this table (and
lattice-init's refiner list).skill-alignflags inventory drift across docs.
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.
- 3d ago First seen · 127 lines · 115 tokens per session scan A efb0be85f6f2
refiners-update is a skill published in the GitHub repository techygarg/lattice (183 stars, last pushed 4d ago), licensed MIT. It adds 115 tokens to every session and 2,045 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
xiaoyaoclaw-workspace-initializer
OpenClaw workspace initialization & standardization. Sets up a proper agent home: standard directory structure (projects/tasks/outputs/knowledge/scripts/ memory/tmp) + WORKSPACE.md rules + multi-agent config safety (config.patch, never config.apply) + memory log. Use when an agent enters a new/empty workspace root, or…
learn
Search, install, update, and rate AI agent skills from agentskill.sh (100,000+ skills). Use when the user asks to find skills, install extensions or plugins, discover new capabilities, check what skills are available, or says "how do I do X" when a skill might help. Also handles listing installed skills, checking for…
review-skill
Review and improve AI agent skills (SKILL.md files) against best practices from the Agent Skills specification and Anthropic's authoring guidelines. Scores skills on 10 quality dimensions, identifies specific issues, and rewrites problem areas. Use when creating, editing, auditing, or improving agent skills. Triggers…
building-chatgpt-apps
Guides creation of ChatGPT Apps with interactive widgets using OpenAI Apps SDK and MCP servers. Use when building ChatGPT custom apps with visual UI components, embedded widgets, or rich interactive experiences. Covers widget architecture, MCP server setup with FastMCP, response metadata, and Developer Mode…
memory-systems
Design and implement memory architectures for agent systems. Use when building agents that need to persist state across sessions, maintain entity consistency, or reason over structured knowledge.
multi-agent-patterns
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.