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/yimwoo/hotl-plugin/requesting-code-reviewnpx skills add yimwoo/hotl-plugin --skill requesting-code-reviewgit clone --depth 1 https://github.com/yimwoo/hotl-pluginWhat 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 | $0.00031 | $0.00834 |
| Opus 5 | $0.00015 | $0.00417 |
| Sonnet 5 | $0.00006 | $0.00167 |
| Haiku 4.5 | $0.00003 | $0.00083 |
Grade A, and why
requesting-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 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HOTL Requesting Code Review
Lifecycle
Executors invoke requesting-code-review at defined checkpoints. This skill dispatches the code-reviewer agent with structured context. Returned findings are handled by receiving-code-review.
Precondition
Only request review when the checkpoint work is in a reviewable state and its planned verification has completed. Do not request review for code that has failing required verification unless the purpose of the review is to diagnose the failure.
When to Request Review
Mandatory Triggers
- executing-plans: After each 3-step batch boundary
- subagent-execution: After meaningful delegated implementation batches (3+ completed implementation steps, or cross-module change, or high-risk/user-facing/shared-infra change)
- All executors: Before final completion (claiming done, merging, or creating a PR)
Conditional Triggers
- loop-execution: At intermediate gates only when the change is high-risk, cross-module, or feature-scale. Always at final completion.
- Ad-hoc development: Before merge to main. Optionally when stuck or before a large refactor.
When NOT to Request
- After trivial single-step changes (typo, config value, import fix)
- Mid-loop iterations that haven't reached a gate
- When the same code was already reviewed and hasn't changed since
- Do not request a second full review when a scoped follow-up review is enough
Review Base (Deterministic)
The review base defines the git range for the reviewer. Executors record this before starting each reviewable batch.
- Batch review:
git rev-parse HEADrecorded by the executor before starting the batch - Final review: Branch point or last recorded review base, whichever is more recent. A final review is required unless the most recent review already covers all current changes and no code changed afterward.
- Follow-up review:
HEADimmediately before the fix. Re-review only the changed scope unless the fix affects shared architecture, risk level, or multiple modules.
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 · 92 lines · 31 tokens per session scan A 5b4d8884bb35
requesting-code-review is a skill published in the GitHub repository yimwoo/hotl-plugin (26 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 834 once invoked, about $0.0002 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
first-plan-co-change-analysis
Skill que constrói o Co-change Graph - "quando arquivo X muda, qual outro arquivo geralmente muda junto?". Use durante Discovery e em /fp:cochange. Baseado em git history. Detecta arquivos co-dependentes que devem ser editados juntos para evitar PRs incompletos. v0.3.0+ usa engine nativo Rust quando disponível…
first-plan-provenance-tracker
Skill que define o schema de proveniência e o sistema de freshness tracking para findings em .first-plan/. Use durante Discovery e refresh para registrar source (file:line@SHA), TTL, confidence inicial e cadeia de supersedeção. Aplica decay de confidence baseado em idade.
first-plan-git-intelligence
Skill que extrai inteligência do git history - heatmap de atividade, ownership, branches/PRs in-flight. Use durante Discovery e em /fp:hot, /fp:owner, /fp:in-flight. Tudo via comandos git read-only.
first-plan-protocol
Esta skill DEVE ser carregada em qualquer comando do plugin first-plan. Define o protocolo PLAN-FIRST (Discovery -> Plan -> Approval -> Execution -> Report), as 7 regras invioláveis e o comportamento esperado em cada fase. Ative quando o usuário invocar /fp: ou mencionar "first-plan", "context compilation", "discovery…
first-plan-reconciliation
Skill que define Spec-Code Reconciliation - matching contínuo entre artefatos de intenção (docs, specs, JIRA, GitHub issues) e implementação (código, testes, PRs). Use durante Discovery e em /fp:check para identificar feature ja implementada, em flight, drifted ou abandonada.
first-plan-semantic-reuse
Skill que faz busca semantica via BM25 sobre o indice de simbolos do projeto. Substitui grep do reuse-index quando o engine nativo esta disponivel. Encontra "preciso de validacao de email" mesmo se a funcao se chama validateEmailRFC. Use durante /fp:reuse e /fp:plan para identificar componentes reusaveis com matching…