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 reviewgit 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/review)<a href="https://agentmods.dev/skills/techygarg/lattice/review"><img src="https://agentmods.dev/badge/skills/techygarg/lattice/review/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/techygarg/lattice/review"><img src="https://agentmods.dev/badge/skills/techygarg/lattice/review.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 | $0.00095 | $0.02878 |
| Opus 5.5 | $0.00038 | $0.01151 |
| Sonnet 5.5 | $0.00019 | $0.00576 |
| Haiku 4.5 | $0.00010 | $0.00288 |
Grade A, and why
review 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 15d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review
Required Skills
Load/apply skills based on scope (see Step 2 for conditional loading):
framework:knowledge-priming-- Load project context (tech stack, architecture, conventions) to evaluate against real standards (always loaded)framework:learning-harvest-- Load prior operational learnings inform review; harvest new patterns at session end (always)framework:collaborative-judgment-- Surface borderline findings with both interpretations instead of silently classifying (always loaded)framework:clean-code-- Code craft: SRP, naming, complexity, error handling (always loaded)framework:architecture-- Structural: layer rules, dependency direction, architectural flows (conditional)framework:domain-driven-design-- Domain modeling: aggregates, entities, value objects (conditional)framework:secure-coding-- Security: trust boundaries, injection, secrets, input handling (conditional)framework:test-quality-- Test: AAA structure, isolation, assertions, naming (conditional)
Config Resolution
Review molecule supports optional config thru review-standards doc from review-refiner (or hand-written). Configures review process — not what atoms check (that's atom-level config via atom refiners).
Resolution steps:
- Look for
.lattice/config.yamlin repo root. - Check for config key
paths.review_standards. - If doc exists at path, read & check YAML frontmatter for
mode:mode: overlay: Read embedded defaults first, then apply doc's sections on top. Sections matched by heading — custom replaces matching defaults, new appended.mode: override(or no mode): Custom doc full precedence. Must be comprehensive.
- If no config or no review-standards doc found, use embedded defaults thruout workflow (full backward compat — identical to review with no config).
Review-standards doc has 7 sections map to workflow steps:
| Section | Affects step |
|---|---|
| §1 Atom Loading Policy | Step 2 (Load Relevant Atoms) |
| §2 Severity Classification | Step 4 (Produce Report) |
| §3 Report Preferences | Step 4 (Produce Report) |
| §4 Scope Rules | Step 1 (Identify the Delta) |
| §5 Insight Capture Preferences | Step 5 (Harvest Learnings and Log Review) |
| §6 Health Log Preferences | Step 5 (Harvest Learnings and Log Review) |
| §7 Custom Review Dimensions | Step 3 (Run Targeted Validation) |
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.
- 15d ago Changed · +10 lines f3edc989affb
- 1mo ago First seen · 206 lines · 95 tokens per session scan A e016d6e8414a
review is a skill published in the GitHub repository techygarg/lattice (209 stars, last pushed yesterday), licensed MIT. It adds 95 tokens to every session and 2,878 once invoked, about $0.0004 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
code-standards
Apply a disciplined engineering workflow to any code change. Use whenever implementing a feature, fixing a bug, or refactoring — before writing code, not after. Walks orient → baseline → smallest change → test → verify → self-review, and enforces language-agnostic hard gates (don't mass-reformat, keep the linter and…
gaia-issue-resolver
End-to-end plan → implement → review pipeline that takes one triaged Gaia issue to a merged-ready PR, with Kill Criteria on the issue and zero follow-up debt. Use when someone says: "resolve this issue", "take #N end-to-end", "work the P0 queue", "fix and ship this issue", "run the resolver", "close out this issue…
release
Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…
gemini
Cross-model second opinion from Google Gemini — a different AI reviewing the same changes, with deep Google ecosystem knowledge. Three modes: review (pass/fail gate for Google Ads campaigns, SEO metadata, or code), challenge (adversarial stress-test that tries to break your changes), and consult (open Q&A with Gemini…
boundaries
Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.
new-skill
Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…