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 denn-gubsky/loomcycle --skill code-reviewgit clone --depth 1 https://github.com/denn-gubsky/loomcycleWrote 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/denn-gubsky/loomcycle/code-review)<a href="https://agentmods.dev/skills/denn-gubsky/loomcycle/code-review"><img src="https://agentmods.dev/badge/skills/denn-gubsky/loomcycle/code-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/denn-gubsky/loomcycle/code-review"><img src="https://agentmods.dev/badge/skills/denn-gubsky/loomcycle/code-review.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 | $0.00049 | $0.00536 |
| Opus 5.5 | $0.00020 | $0.00214 |
| Sonnet 5.5 | $0.00010 | $0.00107 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
code-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 1mo 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Synthesized for loomcycle exp7 from Claude Code's code-reviewer agent + code-review command +
the karpathy-guidelines skill. Methodology for reviewing a slice of a repository with high
precision and minimal false positives.
What to look for
- Project-guideline compliance. Honor the repo's own rules (e.g.
CLAUDE.md): import patterns, error handling, logging, naming, platform compatibility, testing conventions. - Bugs that bite in practice. Logic errors, nil/undefined handling, race conditions, resource leaks, unchecked errors, security issues (injection, secret handling, authz gaps), performance.
- Quality. Significant duplication, missing critical error handling, inadequate test coverage.
Confidence scoring (the precision lever)
Rate each candidate issue 0–100:
- 0 false positive / pre-existing; 25 maybe; 50 real but minor/nit; 75 verified, will hit in practice / guideline-backed; 100 certain, frequent.
- Only report issues with confidence ≥ 80. Quality over quantity — a short list of true issues beats a long list of nits.
Karpathy behavioral guidelines (apply to the review itself)
- Surface assumptions. If a finding depends on an assumption (caller behavior, invariant), say so. If unsure, lower the confidence rather than over-claim.
- Simplicity. Flag overcomplication: speculative abstractions, unrequested configurability, error handling for impossible cases, 200 lines that could be 50.
- Surgical scope. Judge whether changes touch only what they must; flag drive-by edits/refactors and orphaned (newly-unused) imports/vars. Don't demand rewrites of code that isn't broken.
- Verifiable. Prefer findings a developer can act on + verify (a failing case, a concrete fix).
Output per issue
file:line · severity (Critical | Important) · confidence · one-line problem · concrete fix.
Group by severity. If no ≥80 issues in the slice, say so with a one-line "meets standards" summary.
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.
- 1mo ago First seen · 40 lines · 49 tokens per session scan A a9fdc9133ac5
code-review is a skill published in the GitHub repository denn-gubsky/loomcycle (15 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 536 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
compliance-checker
Check affiliate content for FTC compliance and platform rules. Triggers on: "check my content for compliance", "FTC disclosure check", "is this legal", "review for compliance", "check affiliate disclosure", "am I FTC compliant", "audit my content", "compliance review", "legal check", "platform rules check", "check…
self-improver
Review affiliate campaign results and improve strategy. Triggers on: "review my results", "what went wrong", "how to improve conversions", "analyze my campaign", "affiliate retrospective", "why am I not converting", "improve my strategy", "what should I change", "campaign review", "optimize my approach", "learn from…
weknora-shared
Use when driving a WeKnora RAG server through the weknora CLI as an agent — authenticating, managing knowledge bases / documents / sessions / agents, running search or chat, or interpreting the CLI's JSON envelopes and exit codes. Read this before any other weknora- skill.
weknora-rag-search
Use when retrieving from or asking questions against a WeKnora knowledge base via the weknora CLI — and especially when unsure whether to use chat, session ask, or search chunks for a given goal.
control-center-review
Review one captured Control Center build before runtime activation.
rem-investigate-org
The steps for investigating an organisation's page, composed after rem-investigate when the subject is under orgs/.