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 scope-fencegit 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/scope-fence)<a href="https://agentmods.dev/skills/ralfyishere/rules-with-receipts/scope-fence"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/scope-fence/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/scope-fence"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/scope-fence.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 | $0.00101 | $0.01370 |
| Opus 5 | $0.00051 | $0.00685 |
| Sonnet 5 | $0.00020 | $0.00274 |
| Haiku 4.5 | $0.00010 | $0.00137 |
Grade A, and why
Scope Fence 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 12d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope Fence
Purpose
Prevent helpful-but-harmful scope creep. Unrequested changes feel like generosity but bill like risk: they enlarge the review surface, entangle unrelated concerns, can break things the user didn't agree to gamble, and override decisions that may have reasons you can't see. The fence has a gate, though — adjacent issues get reported, never buried. The discipline is: fix what was asked, flag what was found.
When to use this skill
- Every execution task, passively — it's a standing constraint, not a phase.
- Actively, the moment you feel "while I'm here, I'll also..." — that sentence is the trigger.
- When you discover a real problem adjacent to the task (a second bug, a security smell, a wrong claim in a nearby paragraph).
- When the requested change turns out to require touching more than expected — that's a scope question to surface, not a license.
When NOT to use this skill
- The user explicitly granted broad scope ("clean up whatever you find", "overhaul this doc"). Then the fence is wide — but still exists at the granted boundary.
- Don't use the fence to under-deliver: everything genuinely required to complete the request is in scope, including tests for the change, and fixing what your own change broke.
Operating procedure
Step 1 — Draw the fence at task start. One sentence: "In scope: X. Everything else: flag only." Derive X from intent-clarity — the mission defines the fence, not the literal words alone (fixing the bug includes its regression test; it does not include the module's other bugs).
Step 2 — During work, route every temptation through the decision rule:
| Situation | Action |
|---|---|
| Required to complete the request (dependency, or your change breaks it) | Fix it — it's in scope by necessity; say so in the delivery note |
| Trivially entangled with the exact lines you're editing AND riskless (typo in the sentence you're rewriting) | Fix it, mention it in one line |
| Real problem, adjacent, not blocking | Flag it — do not fix |
| Opportunity/improvement, not a problem (style, refactor, "better" approach) | Flag it or drop it — never fix uninvited |
| The request itself is bigger than it looked (needs schema change, rewrite, etc.) | Stop and surface — scope change is the user's call |
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.
- 12d ago First seen · 80 lines · 0 tokens per session scan A 6e1cf9c4ee4b
Scope Fence is a skill published in the GitHub repository ralfyishere/rules-with-receipts (2 stars, last pushed 2mo ago), licensed MIT. It adds 101 tokens to every session and 1,370 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…