Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add mayank-io/mstack/plugin install devWrote 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/mayank-io/mstack/safe-resume)<a href="https://agentmods.dev/skills/mayank-io/mstack/safe-resume"><img src="https://agentmods.dev/badge/skills/mayank-io/mstack/safe-resume/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/mayank-io/mstack/safe-resume"><img src="https://agentmods.dev/badge/skills/mayank-io/mstack/safe-resume.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 | $0.00070 | $0.00607 |
| Opus 5.5 | $0.00028 | $0.00243 |
| Sonnet 5.5 | $0.00014 | $0.00121 |
| Haiku 4.5 | $0.00007 | $0.00061 |
Grade A, and why
safe-resume 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 19d 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Safe Resume
Continue exactly where /dev:safe-pause stopped, in the recorded order, at the recorded boundary, without asking what was happening.
PS below is python3 ${CLAUDE_PLUGIN_ROOT}/scripts/pause_state.py (run --help for the subcommands).
Procedure
- Locate.
PS locate --session-id <id> --cwd <repo>. The id is$CLAUDE_SESSION_IDwhen set, else the id in this session's scratchpad path. No output and exit 1 means there is no pause state: say so in one line and continue with the normal session resume. Do not invent a state. - Read the RESUME.md it prints, frontmatter and body, in full.
- Verify every worktree.
PS verify --resume <path>. Exit 0 means every owned worktree, across every recorded repo, is present, at its recorded tip, and clean. Exit 2 means one is not: stop, repeat the lines it printed naming each worktree and why (tip-moved,dirty,missing), and do not continue. Only MK can decide what to do with a moved tip. Lines startingwarning:are about a primary checkout (primary-tip-moved,primary-changed): a lander may have landed other work, or someone left files there. Report them in one line each and continue. - Re-send the first message from
## First message, and only if the frontmatter records acoordinator. No coordinator: send nothing to anyone. - Run the first command from
## First command, exactly as written. - Mark consumed.
PS mark-resumed --resume <path>so the session-start hook stops announcing it. - Continue in the recorded order: in-flight branches first at their owed step, then the queue. Honour the recorded mode's boundary semantics as
/dev:safe-pausedefines them. Blockers stay blocked until the recorded holder clears them.
Rules
- Never continue past a failed verify. A moved tip means someone else worked here; a dirty tree means a commit was skipped.
- Never re-run a step RESUME.md records as passed. Only owed steps are run.
- Never message a peer the frontmatter does not name.
- The
Peer messages loggedsection is the backlog of who was toldPAUSED; tell each of them the session has resumed, once, in your first message to them.
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.
- 19d ago First seen · 28 lines · 70 tokens per session scan A 13eb57c37607
safe-resume is a skill published in the GitHub repository mayank-io/mstack (6 stars, last pushed 3d ago), licensed MIT. It adds 70 tokens to every session and 607 once invoked, about $0.0003 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 2026-10-13.
Other skills, from other repositories
Dotfiles
Manage /.zshrc and a chosen set of /.config/ directories (you name them in Config.md) against a private GitHub dotfiles repo. Intents: Push (verify private remote, scan secrets), Pull (clone/diff), Sync, Restore (timestamped backup), Status, Backup (local timestamped copy). Security scan blocks .env, secrets, tokens…
conventional-commit
Rules for writing Conventional Commits messages in this project. MUST be invoked every time a commit is created.
python-release
Handle Python SDK release, build, bump, packaging metadata, PyPI client pin, uv.lock, nox/build workflow, and publish verification changes. Use for Python release process work or dependency pin bumps; do not use for ordinary Python feature implementation.
release-notes
Generate and publish concise, evidence-based notes in the body of the latest existing GitHub Release. Use only when the user explicitly invokes $release-notes or explicitly asks to update the latest existing GitHub Release body. Do not invoke for general release planning, changelog, tag, or version tasks.
ratchet-files
Ratchet source file size so every file stays small enough for an agent to read whole: find every file over a token budget, split oversized files by concept, and set up the pre-commit ratchet that stops them from growing. Use when a commit is blocked because a file is over the size budget, when asked to find or split…
git-guardrails-claude-code
A Claude Code setup that blocks selected destructive Git commands before they run. Git is a tool for tracking code changes; the blocked commands include pushing, deleting branches, discarding changes, and hard resets.