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 change-controlgit 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/change-control)<a href="https://agentmods.dev/skills/ralfyishere/rules-with-receipts/change-control"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/change-control/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/change-control"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/change-control.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 | $0.00093 | $0.01399 |
| Opus 5 | $0.00046 | $0.00700 |
| Sonnet 5 | $0.00019 | $0.00280 |
| Haiku 4.5 | $0.00009 | $0.00140 |
Grade A, and why
Change Control 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Change Control
Purpose
A change is good when it does what it intends, does nothing else, and can be understood and undone by someone who isn't you. This skill governs how changes are made — sized, isolated, documented, and reversible — independent of what they are. It applies equally to code, documents, prompts, configs, and strategy plans: anything with a working current state that an edit could damage.
When to use this skill
- Editing anything that currently works or that others depend on.
- Changes that are hard to reverse (sent, deployed, deleted, published, migrated).
- Multi-part edits where review will matter later ("what changed and why?").
- Editing prompts or workflows whose behavior is sensitive to wording.
When NOT to use this skill
- Greenfield creation — nothing exists yet to protect (though
plan-gatestill applies). - Your own scratch work and drafts no one depends on.
Operating procedure
Step 1 — Classify the change by risk before touching anything:
| Class | Definition | Handling |
|---|---|---|
| R0 — Cosmetic | No behavior/meaning change: formatting, typos, comments | Make it. Don't mix it into R2+ changes. |
| R1 — Local, behavior-preserving | Internal restructuring; external behavior/meaning identical | Verify preservation (tests, before/after comparison). |
| R2 — Behavior-changing | Output, meaning, interface, or policy changes | Requires intent statement, verification of both the new behavior and non-regression of the old. |
| R3 — Hard to reverse | Deletes, sends, deploys, migrations, published artifacts, anything external-facing | All of R2, plus a rollback answer before executing, plus explicit confirmation if acting for someone else. |
Step 2 — State intent in one line. "This change makes X do Y because Z." If you can't fill that sentence, you're not ready to edit. If it needs the word "and" twice, it's two changes — split them.
Step 3 — Make the change, honoring the isolation rules:
- One concern per change. Bug fix ≠ refactor ≠ cleanup. Reviewers can verify one intent; they rubber-stamp three.
- No drive-by edits. Adjacent ugliness you noticed goes to the flag list (
scope-fence), not into this diff. - Preserve existing behavior by default. Anything not explicitly targeted should work/read exactly as before — including things you consider bugs (they may be load-bearing).
- Match the local style, even where you'd have chosen differently. Consistency reviews cheaper than taste.
- Keep it minimal but not cryptic: the smallest change that fully accomplishes the intent.
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 · 83 lines · 0 tokens per session scan A 5e57ff552522
Change Control is a skill published in the GitHub repository ralfyishere/rules-with-receipts (2 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 1,399 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…