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 AleksandarBisevac/claude-plugins/plugin install auditWrote 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/commands/aleksandarbisevac/claude-plugins/resume)<a href="https://agentmods.dev/commands/aleksandarbisevac/claude-plugins/resume"><img src="https://agentmods.dev/badge/commands/aleksandarbisevac/claude-plugins/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/commands/aleksandarbisevac/claude-plugins/resume"><img src="https://agentmods.dev/badge/commands/aleksandarbisevac/claude-plugins/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 | $0.00023 | $0.00639 |
| Opus 5 | $0.00012 | $0.00319 |
| Sonnet 5 | $0.00005 | $0.00128 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
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 9d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/audit:resume — continue an interrupted run
Read ${CLAUDE_PLUGIN_ROOT}/reference/orchestrator.md and
${CLAUDE_PLUGIN_ROOT}/reference/manifest-conventions.md first. Run the full preflight
(steps 1–5, including the lock) and emit Progress output (orchestrator) as you go.
Run the Resume after interruption procedure (orchestrator): find the in-progress phase and its
branch, compare committed work, and continue from the first task whose commit is null/missing.
Use after a crash, a lost session, or any interrupted /audit:phase / /audit:next / /audit:run
(/audit:status flags when a phase is resumable). Then follow Reporting and release the lock.
Sweep the interrupted session's record first
Once the in-progress phase is identified and before continuing from the resume point, run:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/governance/commit-audit-state.py" <manifestPath> <phaseId>
This is the point the record of an interrupted run depends on. A gate that was torn down records its row and returns — git belongs to the orchestrator, and a commit made while stopping is how a half-made one happens — so what a lost session leaves behind is a row in the working tree that nothing is going to carry. A task commit would have carried it; an interrupted run never reached one. This is that sweep, and it is the resume entry among the points the orchestrator's Keeping a failed run's record names.
It stages the phase's manifest file, the journal and the evidence directory, and never the
task's files — which is exactly what makes it safe to run here. The interrupted task's
working-tree changes are the thing the orchestrator's own resume step calls untrusted
and refuses to discard without confirmation; this commit must not settle that question in
the other direction by sweeping them into git on its way past. The
exclusion is enforced rather than intended: paths are staged by name, the index is read back
and compared against the same allow-list before anything is committed, and
verify-invariants.py's audit-state-scope re-derives the rule from git afterwards.
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.
- 9d ago First seen · 46 lines · 23 tokens per session scan A acf8daa646be
resume is a command published in the GitHub repository AleksandarBisevac/claude-plugins (4 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 639 once invoked, about $0.0001 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 commands, from other repositories
atomic-commits
Analyze staged changes and organize them into intuitive atomic commits following conventional commits.
sdlc-ship
Phase 4 — Ship. Runs devops-engineer for CI/CD, cloud deploy, and release. Reads verify-handoff.md for clean context.
aw-upgrade
Upgrade gh-aw extension, recompile and validate all workflows, and open a PR with changes.
aw-merge
Merge develop branch to main with PR, CI check, and squash merge.
release-swarm
Orchestrate complex software releases using AI swarms that handle everything from changelog generation to multi-platform deployment.
release-manager
Automated release coordination and deployment with ruv-swarm orchestration for seamless version management, testing, and deployment across multiple packages.