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 ronaknnathani/relay --skill pr-monitorgit clone --depth 1 https://github.com/ronaknnathani/relayWrote 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/ronaknnathani/relay/pr-monitor)<a href="https://agentmods.dev/skills/ronaknnathani/relay/pr-monitor"><img src="https://agentmods.dev/badge/skills/ronaknnathani/relay/pr-monitor/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/ronaknnathani/relay/pr-monitor"><img src="https://agentmods.dev/badge/skills/ronaknnathani/relay/pr-monitor.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 | $0.00062 | $0.02614 |
| Opus 5 | $0.00031 | $0.01307 |
| Sonnet 5 | $0.00012 | $0.00523 |
| Haiku 4.5 | $0.00006 | $0.00261 |
Grade A, and why
pr-monitor 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 7d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Monitor
Handle one pull request attention event, then stop. You are a router: the relay pr watch
runtime does the observing, you interpret its digest, delegate the fixing to pr-fix, re-observe the
pull request, and exit. You never write code, never post in your own voice, never approve, and never
merge.
There is no acknowledgement. The watcher never records that attention was handled, because a local claim can be wrong. Every tick re-reads the live pull request, and an item disappears only when the remote state itself no longer shows it: the check passes or reruns, the head SHA changes, the conflict clears, the thread resolves, your reply lands on that exact source, auto-merge is armed, or the pull request closes or merges. If nothing changed, the problem is still there and it will wake you again — which is correct.
This skill has no loop. It does not schedule, does not recur, and does not own a next-tick time. The watcher owns cadence; one run of this skill owns one digest.
Where the work comes from
Woken by the watcher. The prompt names the project and a fingerprint:
Run pr-monitor once for project <slug> using watcher fingerprint <fp>. Bind them to $SLUG and
$FP, then read the digest that fingerprint names:
relay pr watch digest "$SLUG" --fingerprint "$FP" --json
relay pr watch status "$SLUG" --json # current fingerprint, cadence, last wake, suppression
The digest record is refreshed on every observation, so the pull request metadata and bodies it carries are the newest the watcher saw for that fingerprint — never a stale snapshot.
Invoked manually, or with no Herdr. Observe first, then act on what that observation recorded:
relay pr watch tick "$SLUG" --json # fresh read-only observation; records its digest
tick works with no watcher running and never changes the watcher's schedule. If it returns no
actionable items, there is nothing to do — say so and stop.
What the digest already decided
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.
- 7d ago Changed · +63 lines · -15 tokens per session 15b41d869770
- 12d ago First seen · 118 lines · 77 tokens per session scan A f0d557550848
pr-monitor is a skill published in the GitHub repository ronaknnathani/relay (3 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 2,614 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 2026-08-31.
Other skills, from other repositories
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.
push-ci
Push to remote and monitor CI. Validates branch safety, executes git push WITH explicit user approval, then monitors CI run status via gh CLI. Use when: user says 'push', 'push and watch CI', 'ship it', 'push-ci'. Not for: committing (use /smart-commit), creating PRs (use /create-pr), merging (use /merge-prep).
quality-ci
Set up or refine open-source .NET code-quality gates for CI: formatting, .editorconfig, SDK analyzers, third-party analyzers, coverage, mutation testing, architecture tests, and security scanning. USE FOR: .NET quality gates in CI; analyzer, coverage, mutation, and architecture-test choices; standardizing…
devops-pipeline
Configure pre-commit hooks and lean GitHub Actions for shift-left quality assurance. Use when adding or auditing CI/CD to maximize local test coverage and minimize CI cost. Skip for Terraform/K8s, deployment pipelines, or non-GitHub CI providers.
metalint
Use Metalint in .NET repositories that ship Node-based frontend assets and want one CLI entrypoint over several underlying linters. USE FOR: unified frontend lint commands; combined ESLint, Stylelint, HTMLHint, or similar checks; CI orchestration over multiple frontend linters. DO NOT USE FOR: simple repos where Biome…
conventional-commit
Generer conventional commit-meldinger med Nav-relevante scopes og breaking change-format.