Borrowing it
Nothing to install: this file belongs to mark-weeks/hello-nested-worlds-adventure. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mark-weeks/hello-nested-worlds-adventure/main/.claude/skills/repin-goldens/SKILL.mdgit clone --depth 1 https://github.com/mark-weeks/hello-nested-worlds-adventureWrote 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/mark-weeks/hello-nested-worlds-adventure/repin-goldens)<a href="https://agentmods.dev/skills/mark-weeks/hello-nested-worlds-adventure/repin-goldens"><img src="https://agentmods.dev/badge/skills/mark-weeks/hello-nested-worlds-adventure/repin-goldens/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/mark-weeks/hello-nested-worlds-adventure/repin-goldens"><img src="https://agentmods.dev/badge/skills/mark-weeks/hello-nested-worlds-adventure/repin-goldens.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 | $0.00027 | $0.00665 |
| Opus 5.5 | $0.00011 | $0.00266 |
| Sonnet 5.5 | $0.00005 | $0.00133 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
repin-goldens 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 5d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Re-pinning the golden freeze
A failing pin in tests/test_continuity_freeze.py means "you changed
what new worlds are born as" — not "the test is stale." The store forbids
rewriting born worlds (birth_world is idempotent;
persistence.save_world_nodes refuses overwrites), so the pins guard
births: fresh installs reproducing the reference seed, and every world born
after your change.
Before touching any pin
- Confirm intent from the request and existing ratification. Is changing birth output the point of this diff, or a side effect? A side effect (an accidental extra RNG draw, a reordered bank, a changed breadth range) is a bug — fix the code, not the pin.
- Apply the specific re-pin approval rule in
AGENTS.md's golden-pin covenant. Identify the owner's approval for this pin change in the current task or PR; if missing, ask before changing pins. Present which pins change and why the change is safe (pre-launch vs post-launch matters — after first production birth, seed/name changes go through the ADR-007 continuity process).
The procedure
- Bump
GENERATOR_VERSIONinmultiverse/store.pyfor any meaningful generator change — it keys the born-world store, so old worlds keep their version and new births carry yours. - Re-pin at both depths — the depth-6 reference world AND the full 11-level world. Five scales (Room and deeper) exist only below depth 6; shallow pins alone are blind to their banks. Update every failing surface: node counts, names/world/puzzle digests, breadth profile, landmark canaries, and the renewal-epoch puzzle pins (epochs 1 and 2 — solved-state rehydration keys include "· Renewal N").
- Never re-pin the era-name pins. The two display banks in
multiverse/chronicle.pyare read at render time — editing them retroactively renames every era already displayed. They stay frozen until eras are materialized (ADR-006 "Revisit when"). - Record why in the batch's CHANGELOG entry, and name the re-pin as intentional in the irreversibility check (see the 2026-08-03 and 2026-08-04 entries for the expected shape).
- Run the full
./scripts/check.sh— the freeze suite must pass green on the new pins, with no unexplained changes outside the authorized birth change.
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.
- 5d ago Changed 15f949cda5b4
- 1mo ago Changed · +8 lines · -31 tokens per session 632aaa19f9f6
- 2mo ago First seen · 46 lines · 58 tokens per session scan A 2e12835b52f8
repin-goldens is a skill published in the GitHub repository mark-weeks/hello-nested-worlds-adventure (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 27 tokens to every session and 665 once invoked, about $0.0001 per session on Opus 5.5. 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
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
react-patterns
React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.
golang-testing
Go testing best practices including table-driven tests, test helpers, benchmarking, race detection, coverage analysis, and integration testing patterns. Use when writing or improving Go tests.
verification-loop
A comprehensive verification system for Claude Code sessions. Use when verifying a Claude Code session's work before claiming it is complete.
cli-eval
Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.
qa-test-planner
Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.