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 session-orientationgit 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/session-orientation)<a href="https://agentmods.dev/skills/ralfyishere/rules-with-receipts/session-orientation"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/session-orientation/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/session-orientation"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/session-orientation.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 | $0.00116 | $0.01406 |
| Opus 5 | $0.00058 | $0.00703 |
| Sonnet 5 | $0.00023 | $0.00281 |
| Haiku 4.5 | $0.00012 | $0.00141 |
Grade A, and why
Session Orientation 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 8d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Orientation
Purpose
A fresh session starts with amnesia about everything outside its context window: where repos live, which copy is canonical, what version is current, what is pending. Without a fixed orientation step, every session pays a rediscovery tax — filesystem archaeology, stale-memory guesswork, unscoped audits — and sessions restart instead of compounding. This skill makes orientation a procedure: read the map, verify what matters live, then work — and makes writing the map back a closeout duty, because the read side only works if sessions keep it true.
When to use this skill
- First substantive action in a new or resumed session in a multi-project workspace.
- Project-state requests: "check the work on X", "is GitHub up to date", "continue the launch", "where are we on X" — oblique names count ("the scanner").
- About to
find/glob for a project whose canonical location should be recorded. - About to start a broad audit with no defined scope.
- A session that changed durable project state is about to end (closeout half).
When NOT to use
- Single-project repos where the task names its own files — orientation is one
git status, not a procedure. - Questions with no project-state component.
- Mid-session once oriented — re-run only after resume/compaction, or when
evidence contradicts the map (
memory-hygieneterritory).
The procedure
- Map before territory. Read the workspace registry (
ACTIVE-PROJECTS.mdor whatever CLAUDE.md names) before any filesystem search or audit. Find the entry the request refers to. - Trust order, stated: live observed state > registry > memory files >
recollection. The registry locates truth cheaply; it isn't truth. Live-verify
any registry or memory fact that is load-bearing (the entry's verify commands,
or
git status -sb+ a realgit fetchat minimum). - Canonical path or explain yourself. Work happens in the registry-listed clone. Copies found in scratchpads, temp dirs, or other sessions' workspaces are never source of truth; using one requires saying so and why.
- "Updated/done/published" is a compound claim. Check the parts and name which you checked: tree clean; local == origin after a fetch; CI at HEAD; and for releases: tag position, package registry, one consumer-side check (fresh install or raw URL). A subset checked = a subset claimed.
- Broad requests get scoped by the map: registry pending list + the requester's emphasis, stated as an explicit scope — never an unbounded sweep.
- Closeout writes the map back. Before ending a session that changed state: promote durable work out of scratchpad paths (they die with the session); update the registry entry (state, pending, pitfalls, date). A session that changed state but not the registry is unfinished. No registry yet and the workspace has outgrown one project? Creating a minimal one IS in scope.
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.
- 8d ago First seen · 106 lines · 0 tokens per session scan A 3ba89239c416
Session Orientation is a skill published in the GitHub repository ralfyishere/rules-with-receipts (2 stars, last pushed 1mo ago), licensed MIT. It adds 116 tokens to every session and 1,406 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…