Borrowing it
Nothing to install: this file belongs to in-the-loop-labs/pair-review. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/in-the-loop-labs/pair-review/main/.pi/skills/review-model-guidance/SKILL.mdgit clone --depth 1 https://github.com/in-the-loop-labs/pair-reviewWrote 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/in-the-loop-labs/pair-review/review-model-guidance)<a href="https://agentmods.dev/skills/in-the-loop-labs/pair-review/review-model-guidance"><img src="https://agentmods.dev/badge/skills/in-the-loop-labs/pair-review/review-model-guidance/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/in-the-loop-labs/pair-review/review-model-guidance"><img src="https://agentmods.dev/badge/skills/in-the-loop-labs/pair-review/review-model-guidance.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 | $0.00044 | $0.02957 |
| Opus 5 | $0.00022 | $0.01478 |
| Sonnet 5 | $0.00009 | $0.00591 |
| Haiku 4.5 | $0.00004 | $0.00296 |
Grade A, and why
review-model-guidance 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 12d 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Model Guidance
When performing code review analysis, you can switch models at any time to match
the demands of the task. This applies both to your own direct work and to subtasks
you delegate via the task tool. Use /model to switch your own model, or pass
the model parameter when delegating subtasks.
Before switching models, check which models are actually available by running
${PI_CMD:-pi} --list-models via bash. This shows all models with valid API keys
configured in provider model columns. Specify models as
provider/model. Only switch to models that appear in that list.
Forbidden Models
The following models are never permitted due to extreme cost:
- openai/o3-pro — Prohibitively expensive. Use
openai/o3instead, which provides strong reasoning at a fraction of the cost.
Do not select these models for your own work, subtasks, or any model parameter. If a forbidden model is the only reasoning model available, fall back to a balanced model with extended thinking enabled instead.
When to Switch Models
Not every task benefits from model switching. Use these heuristics:
- Same model is fine when you're doing a single focused task, or when the diff is small enough that model choice won't materially affect quality.
- Switch models when you're delegating subtasks that have clearly different complexity levels, you are reviewing different aspects of the changes, you are reviewing from different perspectives, or when you want a second opinion from a different model family on critical findings.
Model Selection by Task Type
Balanced Models
Use mid-tier models for general code review work:
- File-context analysis: Understanding how changes fit within a file's existing patterns, checking for consistency with surrounding code
- API contract review: Verifying that function signatures, types, and interfaces are used correctly
- Test coverage assessment: Evaluating whether test changes match code changes
- Most general code review: The default choice when you don't have a strong reason to go deeper
- Small to medium diffs: The review itself is straightforward
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.
- 12d ago First seen · 261 lines · 44 tokens per session scan A 46b935e6d593
review-model-guidance is a skill published in the GitHub repository in-the-loop-labs/pair-review (59 stars, last pushed 2d ago), licensed Apache-2.0. It adds 44 tokens to every session and 2,957 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…