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 commands/thomaspinder/impulso/pr-reviewgit clone --depth 1 https://github.com/thomaspinder/ImpulsoWrote 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/commands/thomaspinder/impulso/pr-review)<a href="https://agentmods.dev/commands/thomaspinder/impulso/pr-review"><img src="https://agentmods.dev/badge/commands/thomaspinder/impulso/pr-review.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00923 |
| Opus 5 | $0.00000 | $0.00462 |
| Sonnet 5 | $0.00000 | $0.00185 |
| Haiku 4.5 | $0.00000 | $0.00092 |
Grade A, and why
pr-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review — In-Scope / Out-of-Scope Audit
You are reviewing a pull request. Your job is to audit the changes and produce a structured review with two clearly separated sections: In-Scope items (things that should be fixed in this PR before merge) and Out-of-Scope items (things worth addressing but belonging in separate issues).
1. Gather context
- Read the project's
CLAUDE.md(root and any directory-level files that share a path with changed files) to understand coding standards and review policy. - Run
git diff origin/$BASE_REF...HEAD --name-onlyto list changed files. - Run
git diff origin/$BASE_REF...HEADto inspect the full diff. - Read the PR title, description, and any linked issues for author intent.
2. Classify findings
In-Scope (must be resolved in this PR)
A finding is in-scope if it meets ANY of the following:
- It is a bug, logic error, or correctness issue introduced or exposed by this diff.
- It violates a rule stated in
CLAUDE.mdand the violation is in a changed file/region. - It is a security concern in changed code (injection, auth, data exposure, etc.).
- It is a missing or broken test for new/changed behaviour.
- It is a naming, typing, or API-contract inconsistency introduced by this diff.
- It would block CI or break downstream consumers.
Out-of-Scope (separate follow-up work)
A finding is out-of-scope if it meets ANY of the following:
- It is pre-existing technical debt not introduced by this diff.
- It is a refactoring opportunity in unchanged code.
- It is a performance improvement unrelated to the PR's purpose.
- It is a feature idea or enhancement inspired by the changes.
- It is a documentation gap outside the scope of the changed files.
- It is a broader architectural concern that requires its own design discussion.
When in doubt, classify as out-of-scope — do not block PRs for tangential work.
3. Output format
Structure your review comment as follows. Use exactly this format so it can be parsed by automation:
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.
- 5d ago First seen · 103 lines · 0 tokens per session scan A 679c699c25d6
pr-review is a command published in the GitHub repository thomaspinder/Impulso (23 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 923 tokens. 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 commands, from other repositories
itc-review
Review indirect treatment comparison code and methods for scientific validity and implementation quality.
run-diagnostics
Execute Bayesian models with test data and report convergence diagnostics.
review-model
Review and improve existing Bayesian models for correctness, efficiency, and best practices.
cse-analysis
Full Clinical Scenario Evaluation workflow using Mediana framework.
itc-analysis
Orchestrate indirect treatment comparison workflows across pairwise meta-analysis, NMA, MAIC, STC, and ML-NMR.
create-model
Interactive workflow for creating Bayesian models in Stan, JAGS, WinBUGS, or PyMC.