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 live-state-truthgit 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/live-state-truth)<a href="https://agentmods.dev/skills/ralfyishere/rules-with-receipts/live-state-truth"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/live-state-truth/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/live-state-truth"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/live-state-truth.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 | $0.00113 | $0.01424 |
| Opus 5 | $0.00056 | $0.00712 |
| Sonnet 5 | $0.00023 | $0.00285 |
| Haiku 4.5 | $0.00011 | $0.00142 |
Grade A, and why
Live State Truth 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 10d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Live State Truth
Purpose
The world changes; memory doesn't. Files get edited, tests start failing, docs drift from code, and your own recollection of "what that file says" degrades within a long session. The rule: any claim about current state must trace to an observation made in this session — and recently enough that nothing you did since could have changed it. Everything else is a guess wearing a fact's clothes.
When to use this skill
- Before editing any file (read it first — its current content, not your memory of it).
- Before claiming code behavior: run it, test it, or read the actual source path that executes.
- After making changes: run the thing. "Should work now" is a prediction, not a result.
- When debugging: read the actual error text, full and verbatim — not a paraphrase.
- For non-coding work: before saying "the document/data/brief says X", find and quote the actual passage.
- After any interruption: resumed session, compacted context, or a long detour. Re-anchor before continuing.
When NOT to use this skill
- Stable general knowledge that no observation would change (algorithmic facts, language semantics).
- Re-reading a file you read two actions ago and haven't touched — that's ritual, not verification. The test: could anything have changed it since I looked?
Operating procedure
For coding and file work:
- Before editing: read the target file (at least the region you'll touch and its surroundings). Edits based on remembered content routinely miss that the file already changed.
- Before claiming behavior: prefer running over reading, reading over remembering. Check the installed version of a dependency, not the version you assume.
- Errors: capture the full message, stack trace, and the exact command that produced it. Half the diagnosis is usually sitting in the part of the error nobody read.
- After changes: execute the verification — run the test, hit the endpoint, build the project. Report what happened, with output, not what should happen. If you can't run it, say so explicitly: "not executed; verified by reading only."
- Environment claims (what's installed, what's running, what a config is set to): one command to check beats any assumption.
which,--version,env, reading the actual config file.
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.
- 10d ago First seen · 79 lines · 0 tokens per session scan A b65dec96972c
Live State Truth is a skill published in the GitHub repository ralfyishere/rules-with-receipts (2 stars, last pushed 2mo ago), licensed MIT. It adds 113 tokens to every session and 1,424 once invoked, about $0.0006 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…