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 ralfyishere/rules-with-receipts --skill proactive-rigorgit clone --depth 1 https://github.com/ralfyishere/rules-with-receiptsWrote 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/ralfyishere/rules-with-receipts/proactive-rigor)<a href="https://agentmods.dev/skills/ralfyishere/rules-with-receipts/proactive-rigor"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/proactive-rigor/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/ralfyishere/rules-with-receipts/proactive-rigor"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/proactive-rigor.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00095 | $0.01292 |
| Opus 5 | $0.00048 | $0.00646 |
| Sonnet 5 | $0.00019 | $0.00258 |
| Haiku 4.5 | $0.00010 | $0.00129 |
Grade A, and why
Proactive Rigor 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 9d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proactive Rigor
Purpose
Deliver what was asked and flag what the user couldn't see from where they stood — without turning every task into an audit. The value of a senior collaborator isn't just executing requests; it's noticing the unasked question. The discipline is in the delivery: flags are compact, ranked, and attached to the work, never a gate in front of it.
When to use this skill
- The request omits a constraint that will matter (audience unspecified for a doc, error handling unspecified for an integration, timezone unhandled in a date feature).
- Input material contains gaps, contradictions, or numbers that don't add up — even if the task wasn't "check this."
- A conclusion or decision rests on evidence that wouldn't survive one probing question.
- A term doing heavy lifting is undefined ("make it scalable", "the important users", "done by Q3").
- You can see a second-order effect the user likely can't (this change breaks that consumer; this pricing works until the discount stacks).
When NOT to use this skill
- The user asked for a quick draft, a brainstorm, or an explicitly rough pass — match their register.
- Low stakes and reversible: a flag on a throwaway script is noise.
- The "issue" is a style preference, not a defect. Rigor is about consequences, not taste.
- You already flagged it once. One flag is a service; repeating it is nagging.
Operating procedure
Step 1 — Do the requested work. Rigor rides along; it doesn't ride in front. Never hold the deliverable hostage to concerns (unless the concern makes the work itself unsafe — then say so immediately).
Step 2 — While working, keep a flag ledger. Anything that pattern-matches to:
- Missing constraint — a decision you had to make that the user probably has an opinion on.
- Hidden risk — a way this goes wrong later that the request didn't anticipate.
- Weak evidence — a load-bearing claim (theirs or in the source material) resting on little.
- Undefined term — a word whose interpretation changes the work.
- Downstream problem — a cost that lands after this task ships.
- Contradiction — the material disagrees with itself or with known facts.
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.
- 9d ago First seen · 89 lines · 0 tokens per session scan A ef0a9943ac73
Proactive Rigor is a skill published in the GitHub repository ralfyishere/rules-with-receipts (2 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 1,292 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
setup-matt-pocock-skills
A setup skill that configures engineering skills for a repository, including its issue tracker, labels, and documentation layout. A repository is the project folder managed by version control.
frontend-design
A design guide for building polished web interfaces such as pages, dashboards, forms, navigation, and reusable UI components. It covers HTML, CSS, JavaScript, and common frontend frameworks.
alterlab-cobrapy
Build and analyze genome-scale constraint-based metabolic models with COBRApy — flux balance analysis (FBA), flux variability analysis (FVA), gene and reaction knockouts, flux sampling, and SBML model I/O. Use when simulating metabolic networks, predicting growth or knockout phenotypes, or running systems-biology and…
alterlab-depmap
Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity data, and gene effect profiles. Use when identifying cancer-specific genetic vulnerabilities, finding synthetic lethal interactions, checking whether a gene is essential in given cell lines, or…
alterlab-qutip
Simulates open quantum systems with QuTiP, the Quantum Toolbox in Python, solving Lindblad master equations (mesolve), Monte Carlo trajectories (mcsolve), and unitary dynamics (sesolve). Use when studying master-equation or Lindblad dynamics, decoherence, dissipation, quantum optics, cavity QED, or open-system time…