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.
npx skills add makifbaysal/tasktrooper --skill batch-artifact-verificationgit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/makifbaysal/tasktrooper/batch-artifact-verification)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/batch-artifact-verification"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/batch-artifact-verification/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/makifbaysal/tasktrooper/batch-artifact-verification"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/batch-artifact-verification.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 | $0.00047 | $0.01018 |
| Opus 5.5 | $0.00019 | $0.00407 |
| Sonnet 5.5 | $0.00009 | $0.00204 |
| Haiku 4.5 | $0.00005 | $0.00102 |
Grade A, and why
batch-artifact-verification 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 8d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Batch artifact verification
A batch release (desktop, mobile and other human-cut components) has no bound runtime environment — see post-deploy-verification's last section. Its evidence is whether the thing it built actually got published and is what users will fetch next, per executor.
github_actions / local
run_terminal("gh release view <tag> --json tagName,isDraft,isPrerelease,isImmutable,publishedAt,assets")
Expect isDraft: false, the platform's assets present with size > 0, and the update-feed file if the app ships one (e.g. latest-mac.yml). If gh is unavailable but the repository is public, fall back to fetch_url https://api.github.com/repos/<owner>/<repo>/releases/tags/<tag>.
If the repository brief names an update feed or a Homebrew cask URL, fetch_url it and confirm it names the new version — that is what actually reaches an existing install, not the GitHub Release page by itself.
For a local executor, the exit code is the first signal: local_run.exit_code == 0, with local_run.tail showing the publish step actually ran (not just that the build compiled).
store
Every entry in store_builds[] must have build != baseline_build and carry no error. A baseline_build of "?" means the baseline was never confirmed — say so rather than treating it as a pass. "Deployed" here means the build reached the internal/testing channel; promoting it to production is a human step taken in the store console, and your finish note says so explicitly rather than implying the rollout is live.
Yanking a bad batch release
This is the first manual_steps item on a batch rollback (rollback-runbook), and you perform it yourself — it is the one write release-terminal-scope allows:
run_terminal('gh release edit <tag> --prerelease --title "<name> [YANKED]"')
This works on an immutable release (title, notes and prerelease/latest stay editable; assets and the tag itself do not) and removes it from GitHub's "latest" resolution (the most recent non-prerelease, non-draft release), which most update feeds follow via /releases/latest. Then point "latest" back at the previous good release:
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.
- 8d ago First seen · 56 lines · 47 tokens per session scan A 0344f927b298
batch-artifact-verification is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 47 tokens to every session and 1,018 once invoked, about $0.0002 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 2026-10-05.
Other skills, from other repositories
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
touch-release
Set up mobile release pipeline — Fastlane, code signing, CI, beta distribution, versioning. Use when asked about "app store setup", "release pipeline", "fastlane", "beta distribution", or "signing".
ramp
Fetch and follow Ramp's published agent playbooks inside Paperclip, with mandatory approval gates for spend, incorporation, cards, account setup, and other financial actions.
paperclip-create-agent
Create new agents in Paperclip with governance-aware hiring. Use when you need to inspect adapter configuration options, compare existing agent configs, draft a new agent prompt/config, and submit a hire request.
paperclip-task-bridge
Create, comment on, update, and list Paperclip tasks from Hermes using scoped Paperclip API credentials.