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 OpenHands/extensions --skill github-delivery-watchdoggit clone --depth 1 https://github.com/OpenHands/extensionsWrote 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/openhands/extensions/github-delivery-watchdog)<a href="https://agentmods.dev/skills/openhands/extensions/github-delivery-watchdog"><img src="https://agentmods.dev/badge/skills/openhands/extensions/github-delivery-watchdog/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/openhands/extensions/github-delivery-watchdog"><img src="https://agentmods.dev/badge/skills/openhands/extensions/github-delivery-watchdog.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 | $0.00026 | $0.00413 |
| Opus 5.5 | $0.00010 | $0.00165 |
| Sonnet 5.5 | $0.00005 | $0.00083 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
github-delivery-watchdog 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 1mo 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.
What it actually says
GitHub delivery watchdog
This is a deterministic scheduled host command. It creates no agent or conversation and needs no agent profile. Configure a repository-scoped fine-grained PAT with Contents and Issues read/write plus Pull requests, Actions, Commit statuses, and Metadata read. Contents write permits merge; Issues write retains the review label when the branch is updated. Never put the token value in the automation definition.
Package scripts/worker.py as worker.py and the shared
scripts/github_client.py as github_client.py.
The catalog bundle declares these exact files. Its config.json supplies
repos, branch_prefix, and the saved secret name. The shared GitHub client
resolves only that named secret. Automation owns scheduling and cancellation.
Set branch_prefix (default openhands/issue), base_branch (defaults to the repository's default branch),
and required_workflow_ids when particular Actions workflows must run. The
watchdog requires software-factory/tests and software-factory/review success
statuses on the exact head, all other statuses and Actions passing, a current
base, a non-draft PR, and GitHub reporting it mergeable. Missing, pending, failed,
or inaccessible evidence does not permit merge. A changed head requires fresh
review and tests. When an accepted branch is behind the base, the watchdog asks
GitHub to update it and retains the review trigger label; it considers the new
head only on a later run. The merge request includes the expected head SHA.
Actions are optional when required_workflow_ids is empty; the two acceptance
statuses remain mandatory. Configure workflow IDs when GitHub Actions must also
supply evidence. Branch protection remains GitHub's final merge gate.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 36 lines · 26 tokens per session scan A 536cb76358c7
github-delivery-watchdog is a skill published in the GitHub repository OpenHands/extensions (167 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 413 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 2026-09-17.
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.
agent-github-modes
Agent skill for github-modes - invoke with $agent-github-modes.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
atmos-hooks
Atmos hooks: lifecycle events, hook kinds, command/store/git/security hooks, step/steps hooks, when: conditions, scoping and overrides, toolchain integration, --skip-hooks, and Atmos Pro/local output.
atmos-pro
Atmos Pro setup and workflows: settings.pro, GitHub OIDC, affected and inventory uploads, stack locks, pro commit, workflow dispatch, merge queues, and drift detection.