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 plan-gategit 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/plan-gate)<a href="https://agentmods.dev/skills/ralfyishere/rules-with-receipts/plan-gate"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/plan-gate.svg" alt="Measured on agentmods" 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 | $0.00108 | $0.01361 |
| Opus 5 | $0.00054 | $0.00681 |
| Sonnet 5 | $0.00022 | $0.00272 |
| Haiku 4.5 | $0.00011 | $0.00136 |
Grade A, and why
Plan Gate 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 7d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Gate
Purpose
Prevent rushed execution. A wrong start on complex work wastes more time than any plan costs. The gate: before making the first change on non-trivial work, a plan must exist in writing — visible to the user, not just implied.
Equally important: do not over-plan. A trivial task with a ceremony plan is as much a failure as a complex task with no plan.
When to use this skill
- The task has 3+ dependent steps, touches multiple files/sections, or has unclear requirements.
- The cost of a wrong start is high (large edits, irreversible actions, external-facing output).
- You feel the urge to "just start" on something you can't fully picture the end state of. That urge is the trigger.
When NOT to use this skill
- Single obvious step, reversible, under ~2 minutes of work (typo fix, rename, direct factual answer). Just do it.
- The user provided the plan and asked you to execute it. Confirm you understand it; don't rewrite it.
- Pure exploration/reading with no changes — go straight to
live-state-truthinstead.
Operating procedure
Step 1 — Pick the planning depth. Do this in your head; it takes five seconds.
| Depth | Task size signals | Plan required |
|---|---|---|
| 0 — None | One step, obvious, reversible | None. Execute. |
| 1 — Micro | 2–5 steps, familiar territory, low blast radius | One short paragraph: goal, steps, done-check |
| 2 — Structured | Multi-file / multi-section, some unknowns, moderate stakes | Full template below |
| 3 — Staged | Large, unfamiliar, or risky; can't hold it all in one plan | Template below + hand decomposition to deep-decomposition; plan only stage 1 in detail |
Step 2 — Write the plan (Depth 2–3 template):
## Plan: <one-line goal>
**Success criteria:** How we'll know it worked — observable, checkable.
**Constraints:** Stated by the user + inferred (style, compatibility, deadline pressure).
**Assumptions:** What I'm taking as true without proof. (Each is a risk.)
**Risks:** Top 2–3 ways this goes wrong, and the mitigation for each.
**Steps:** First 3–5 concrete actions. (Later steps may be rough.)
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.
- 7d ago First seen · 93 lines · 108 tokens per session scan A e264c08de6b9
Plan Gate is a skill published in the GitHub repository ralfyishere/rules-with-receipts (2 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 1,361 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…