mav-durability-on-gh

mav-durability-on-gh is a skill for Claude Code from thermiteau/maverick. It costs 58 tokens per session (1,902 once invoked), scanned A, original, Apache-2.0.

Guidance for preserving the state of Maverick work across machines and interrupted runs by storing it on GitHub. Local files are treated as temporary copies, while GitHub is the shared source of truth.

In plain words
What is it for?
Use it for multi-machine or parallel workflows, cold-start recovery, durable progress markers, claims and leases, and pushing completed work so another instance can resume it.
Why use it?
It prevents a crashed machine or lost worktree from losing the information needed to continue. Other workflow instances can recreate progress from remote branches and issue markers.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions subagents.

Part of the maverick plugin — 41 skills, 5 agents, 5 hooks shipped together

Good fit Use it for multi-machine or parallel workflows, cold-start recovery, durable progress markers, claims and leases, and pushing completed work so another instance can resume it.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thermiteau/maverick/mav-durability-on-gh
Install

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.

Any agent
npx skills add thermiteau/maverick --skill mav-durability-on-gh
Clone the repo
git clone --depth 1 https://github.com/thermiteau/maverick

Made for: Claude Code.

Or install maverick, the plugin that ships this one along with the rest of its 41 skills, 5 agents, 5 hooks.

Wrote 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.

agentmods badge for mav-durability-on-gh

README.md
[![agentmods](https://agentmods.dev/badge/skills/thermiteau/maverick/mav-durability-on-gh/github.svg)](https://agentmods.dev/skills/thermiteau/maverick/mav-durability-on-gh)
Your own site
<a href="https://agentmods.dev/skills/thermiteau/maverick/mav-durability-on-gh"><img src="https://agentmods.dev/badge/skills/thermiteau/maverick/mav-durability-on-gh/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.

agentmods 80×15 button for mav-durability-on-gh

Your own site · 80×15
<a href="https://agentmods.dev/skills/thermiteau/maverick/mav-durability-on-gh"><img src="https://agentmods.dev/badge/skills/thermiteau/maverick/mav-durability-on-gh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,902 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.01902
Opus 5 $0.00029 $0.00951
Sonnet 5 $0.00012 $0.00380
Haiku 4.5 $0.00006 $0.00190

Measured 11d ago against content hash 317a8895aa50, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mav-durability-on-gh 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 11d 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.

skills/mav-durability-on-gh/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Durability on GitHub

Maverick runs on many machines concurrently. Any one of them can die without notice. The only way to make the workflow crash-safe is to treat GitHub as the source of truth and treat local files as a derivable cache.

Principle

Every piece of state that another Maverick instance might need to resume your work must be on GitHub before you move to the next step. If the only copy of a piece of state is in your local filesystem, losing it loses the run.

Markers — the durable state surface

Maverick persists workflow state to GitHub as fenced JSON code blocks inside issue comments. Each block is tagged with a kind-specific language marker so another instance can find and parse it reliably.

Marker Lives on Purpose
maverick-dag epic issue Machine-readable DAG of stories and their deps
maverick-state epic issue Rolling epic-state snapshot (merged / in_flight / blocked / ejected)
maverick-claim each claimed issue Atomic claim record (instance-id, host, scope)
maverick-lease each claimed issue Heartbeat lease (expiry timestamp, refreshed periodically)
maverick-bprop epic issue Block-propagation in-flight marker (resume if present)

A marker looks like this inside a comment body:

```maverick-state
{
  "epic": 123,
  "stories": {"140": "merged", "142": "in_flight"},
  "updated_at": "2026-04-23T10:15:00Z"
}

The canonical read/write surface is `uv run maverick gh-state …` (backed by
`src/maverick/gh_state.py`). Skills should call the CLI; they should not
re-implement marker parsing.

## Cold-start hydration

At the top of every run, assume your local filesystem is stale or empty and
rebuild context from GitHub:

```dot
digraph hydrate {
    "Session starts" [shape=box];
    "Identify target issue / epic" [shape=box];
    "Read maverick-dag marker" [shape=box];
    "Read maverick-state marker" [shape=box];
    "Read claim / lease / block labels" [shape=box];
    "Read open PRs and CI status" [shape=box];
    "bprop marker present?" [shape=diamond];
    "Resume block-propagation" [shape=box];
    "Local cache hydrated" [shape=box];

    "Session starts" -> "Identify target issue / epic";
    "Identify target issue / epic" -> "Read maverick-dag marker";
    "Read maverick-dag marker" -> "Read maverick-state marker";
    "Read maverick-state marker" -> "Read claim / lease / block labels";
    "Read claim / lease / block labels" -> "Read open PRs and CI status";
    "Read open PRs and CI status" -> "bprop marker present?";
    "bprop marker present?" -> "Resume block-propagation" [label="yes"];
    "bprop marker present?" -> "Local cache hydrated" [label="no"];
    "Resume block-propagation" -> "Local cache hydrated";
}

Read the full file on GitHub · 188 lines

Changes

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.

  1. 11d ago First seen · 188 lines · 58 tokens per session scan A 317a8895aa50

Subscribe to this mod's changes

mav-durability-on-gh is a skill published in the GitHub repository thermiteau/maverick (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,902 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

prowler-commit

Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.

prowler-cloud/prowler · 33 tokens

gh-auth-isolation

Safely manage multiple GitHub identities (EMU + personal) in agent workflows.

github/gh-aw · 20 tokens

comet-github

A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.

rpamis/comet · 72 tokens

github-skill

Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.

zeenie-ai/OpenCompany · 51 tokens

changelog-composer

Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".

Mathews-Tom/armory · 67 tokens

re0-merge

Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…

LilMGenius/paperthin · 70 tokens