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/prgit clone --depth 1 https://github.com/thomaspinder/ImpulsoWhat 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 | $0.00510 |
| Opus 5 | $0.00000 | $0.00255 |
| Sonnet 5 | $0.00000 | $0.00102 |
| Haiku 4.5 | $0.00000 | $0.00051 |
Grade A, and why
pr 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 2d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pr — Create a PR summarising changes vs main
Analyse the diff between the current branch and main, then open a pull request using the GitHub CLI (gh).
Steps
- Run
git diff main...HEADto get the full diff. - Run
git log main..HEAD --onelineto get the commit list. - Analyse the diff and commits to understand the nature of the changes.
- Classify the change into exactly one primary category and assign the corresponding label:
| Category | PR title prefix | GitHub label |
|---|---|---|
| New feature | feat: |
enhancement |
| Bug fix | fix: |
bug |
| Breaking change | feat!: / fix!: |
breaking-change |
| Documentation | docs: |
documentation |
| Refactor | refactor: |
internal |
| Testing | test: |
internal |
| Chore / CI | chore: |
internal |
| Performance | perf: |
performance |
-
Write the PR title in imperative mood with the appropriate prefix.
-
Write the PR body using this structure:
Body
## Summary
2–3 sentences: what this PR does and why.
## Changes
- Key changes grouped logically (not one per file).
## Testing
How changes were tested, or note if tests are included.
## Notes
Breaking changes, migration steps, deprecations, or follow-ups.
-
Request feedback from me around the PR title and body before creating the PR. I may ask for revisions to ensure clarity and completeness.
-
Only once you have my approval, create the PR:
gh pr create \
--title "<prefix>: <title>" \
--body "<body>" \
--label "<label>"
If the label doesn't exist yet, create it first with gh label create.
Rules
- Do NOT fabricate changes — only describe what is in the diff.
- Always assign exactly one category label.
- If the change is breaking, mention it explicitly in the Summary and Notes sections.
- If the diff is empty, stop and inform me.
- If
ghis not authenticated, tell me to rungh auth login.
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.
- 2d ago First seen · 59 lines · 0 tokens per session scan A 6b3b41905496
pr is a command published in the GitHub repository thomaspinder/Impulso (23 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 510 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.
cse-analysis
Full Clinical Scenario Evaluation workflow using Mediana framework.
review-model
Review and improve existing Bayesian models for correctness, efficiency, and best practices.
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.