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 Jamie-BitFlight/claude_skills --skill code-review-llmgit clone --depth 1 https://github.com/Jamie-BitFlight/claude_skillsWrote 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/jamie-bitflight/claude_skills/code-review-llm)<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/code-review-llm"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/code-review-llm/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/jamie-bitflight/claude_skills/code-review-llm"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/code-review-llm.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 | $0.00056 | $0.01309 |
| Opus 5.5 | $0.00022 | $0.00524 |
| Sonnet 5.5 | $0.00011 | $0.00262 |
| Haiku 4.5 | $0.00006 | $0.00131 |
Grade A, and why
code-review-llm 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 7d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Integration Code Review Patterns
Stack-specific rules loaded by dh:code-reviewer when prompt files, model selection logic, or evaluation harness code are detected.
Load /dh:review-principles before applying these checks. Verify model identifiers, request
parameters, and error semantics against the provider and SDK version the target actually uses.
Prompt Hygiene
- Keep instruction authority distinguishable from user/retrieved content. Trace where untrusted text can influence instructions, tool arguments, or consequential actions.
- Check that user-controlled content is treated as data at its intended boundary. String interpolation, escaping, role separation, or templating alone does not establish resistance to prompt injection.
- Review prompt composition for accidental instruction mixing, missing delimiters, or lost context using concrete inputs; do not report every f-string as an injection defect.
- Recommend dedicated prompt resources when versioning, reuse, or review clarity benefits; do not impose a line-count rule on inline strings.
Model Selection
- Evaluate the selected model against the task's quality, cost, latency, and reproducibility requirements using relevant evidence. Do not infer a cost or quality regression solely from a tier name or task label.
- Check the selection rationale and configuration ownership, including fallback behavior when the chosen model is unavailable.
- Verify that model identifiers are valid for the provider API or harness field being used. Choose pinned identifiers or aliases according to the target's reproducibility/update contract; do not substitute harness tier names into an unrelated API.
# The configured identifier must match the selected provider and release policy.
model = config.model_identifier
Context Management
- Trace context growth against the selected model's input/output budgets and the application's supported workload; report overflow or loss of required context with the affected scenario.
- Check that any truncation, summarization, or retention strategy preserves the task's important instructions, evidence, and state. Turn count alone does not determine context size.
- Token count must be tracked and logged — silent context truncation is harder to debug than explicit overflow handling
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.
- 7d ago Changed · -1 lines be95eeb234ef
- 15d ago Changed · -5 lines · -17 tokens per session 68e75b36ba5b
- 1mo ago First seen · 119 lines · 73 tokens per session scan A 15e7d17bc94d
code-review-llm is a skill published in the GitHub repository Jamie-BitFlight/claude_skills (67 stars, last pushed 4d ago), licensed MIT. It adds 56 tokens to every session and 1,309 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 2026-09-03.
Other skills, from other repositories
promptkit
PromptKit composition engine. Use this skill when the user wants to assemble a task-specific prompt, write a requirements doc, investigate a bug, review code, plan an implementation, author agent instructions, create a Copilot prompt file, build an agentic workflow, or perform any engineering task that PromptKit has a…
habit-hooks-prompting
Write or revise a habit-hooks coaching prompt. Use when a linter / knip / jscpd rule fires and the agent's default fix is wrong or shallow, or when adding a project-local override prompt. Keeps prompts short and outcome-focused using the ROSE pattern.
meta-prompting
Enhanced reasoning patterns via slash commands (/think, /verify, /adversarial, /edge, /compare, /confidence, /budget, /constrain, /json, /flip, /assumptions, /tensions, /analyze, /trade) or natural language ("argue against", "what could break", "show reasoning", "deep review", "meta-prompts", "thinking modes"…
bootstrap
Alias for the /promptkit skill. Use this when the user wants to assemble a task-specific prompt using PromptKit, or says "bootstrap" to start the PromptKit composition engine.
jev-opportunity-scout
Analisa o projeto atual em busca de decisões semânticas implementadas de forma frágil — cadeia de if/else com string matching, regex de classificação, palavra-chave hardcoded, ou chamada de LLM genérica fazendo prompt-and-parse pra extrair categoria/score/booleano — e aponta onde substituir por um judgment tipado do…
review-prompt
Review LLM prompts against the prompt-engineering skill's principles — leading with where each line came from — and report the findings without modifying files. Use when reviewing prompt quality, auditing a prompt, evaluating a system prompt, or checking whether prompt issues are high-confidence and fixable.