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/irreversibility-check/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/irreversibility-check)<a href="https://agentmods.dev/skills/mark-weeks/hello-nested-worlds-adventure/irreversibility-check"><img src="https://agentmods.dev/badge/skills/mark-weeks/hello-nested-worlds-adventure/irreversibility-check/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/irreversibility-check"><img src="https://agentmods.dev/badge/skills/mark-weeks/hello-nested-worlds-adventure/irreversibility-check.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 | $0.00028 | $0.01058 |
| Opus 5.5 | $0.00011 | $0.00423 |
| Sonnet 5.5 | $0.00006 | $0.00212 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
irreversibility-check 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Irreversibility check
Assess the diff when documenting a change batch or preparing its PR/merge. Record the result even for a draft whose verification is incomplete; the canonical checks still must pass before proposing merge. Human questions apply only to a tripped one-way door whose decision has not already been ratified.
Procedure
-
Identify the actual comparison scope. For a PR, use its current head and actual base (refresh the relevant remote ref when needed); a stale local
maincan falsely trip or hide a door. For an uncommitted local batch, inspect its staged and unstaged changes plus new files. Read the relevant hunks below and exclude unrelated pre-existing work. Do not create or fetch a PR merely to assess a local documentation edit. -
Answer each question from the diff, with the file that proves it:
- Golden re-pin? Any change to the pinned digests/canaries in
tests/test_continuity_freeze.py, the content banks or breadth ranges inmultiverse/generator.py, orGENERATOR_VERSIONinmultiverse/store.py. A bank edit changes what NEW worlds are born as (born worlds are immune —TestBankEditImmunity); a pin change must be conscious. If yes, therepin-goldensskill is the procedure. - Migration added or altered? Anything under
persistence/migrations/. Migrations are additive only — new tables or new columns with defaults; never a destructive rewrite ofworld_mutations,agent_memory,puzzle_results, orworld_nodes. - New
world_mutationswrite path or chronicle row? New call sites ofpersistence.record_mutation(or any new INSERT intoworld_mutations). The chronicle is append-only with exactly three sanctioned maintenance mechanisms (redaction, double-gated pruning, disaster restore) — a new write path is a covenant-level change. - World-meta pin touched?
world_metarows are write-once first-selection records (ADR-008: the wrap hinge) — the stored value IS the fact from then on. Any newpersistence.pin_world_metacall site, any change to a pinning rule (e.g. the hinge selector inmultiverse/wrap.py) that runs before first production pin, or — never acceptable without an ADR — any code path that would rewrite a pinned row. Selector edits after a world is pinned cannot move it (TestSelectorEditImmunity), so the danger window is pre-pin tuning and new pin keys. - Era display banks touched? The two banks in
multiverse/chronicle.pyare read at render time and stay frozen (exact strings pinned) until eras are materialized (ADR-006).
- Golden re-pin? Any change to the pinned digests/canaries in
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 263c41ccab53
- 1mo ago Changed · +5 lines a6f80590868c
- 1mo ago Changed · +2 lines · -59 tokens per session b25ed2e69434
- 1mo ago Changed · +10 lines 4fd566a5548d
- 2mo ago First seen · 67 lines · 87 tokens per session scan A 8769862657d3
irreversibility-check 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 28 tokens to every session and 1,058 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
deployment-patterns
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up deployment infrastructure or planning releases.
version-bump
Automated semantic versioning and release workflow for Claude Code plugins. Handles version increments across package.json, marketplace.json, plugin.json manifests, build verification, git tagging, GitHub releases, and changelog generation. npm publishing is done by the tag-triggered GitHub Actions workflow through…
emerging-techniques-model-merging
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task…
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
release
Fully automate a release with version-bump and childhood.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.