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 agentmods add skills/d-o-hub/github-template-ai-agents/github-pr-sentinelnpx skills add d-o-hub/github-template-ai-agents --skill github-pr-sentinelgit clone --depth 1 https://github.com/d-o-hub/github-template-ai-agentsWrote 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/d-o-hub/github-template-ai-agents/github-pr-sentinel)<a href="https://agentmods.dev/skills/d-o-hub/github-template-ai-agents/github-pr-sentinel"><img src="https://agentmods.dev/badge/skills/d-o-hub/github-template-ai-agents/github-pr-sentinel.svg" alt="Measured on agentmods" 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 | $0.00089 | $0.02522 |
| Opus 5 | $0.00044 | $0.01261 |
| Sonnet 5 | $0.00018 | $0.00504 |
| Haiku 4.5 | $0.00009 | $0.00252 |
Grade A, and why
github-pr-sentinel 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 3d 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Sentinel
Monitor a GitHub pull request persistently until one of these terminal outcomes occurs.
When to Use
- User asks to monitor a PR, watch CI, or babysit a pull request
- Need to handle review comments or keep an eye on failures and feedback
Terminal Outcomes (stop when any is true)
- PR merged or closed — stop immediately on confirmation.
- PR ready to merge — CI green, no unaddressed review comments, not blocked on required review approval, no merge conflict risk.
- User help required — CI infrastructure issues, exhausted flaky retries (3 cycles), permission problems, or ambiguous situations that cannot be resolved safely.
Do not stop merely because a snapshot returns idle while checks are still pending.
Inputs
Accept any of:
- No argument: infer PR from current branch (
--pr auto) - PR number
- PR URL
Core Workflow
- When asked to "monitor"/"watch"/"babysit" a PR, start with
--watch(continuous mode) unless doing a one-shot diagnostic. - Run the watcher script to snapshot PR/CI/review state.
- Inspect the
actionslist in the JSON response. - If
diagnose_ci_failureis present, inspect failed run logs and classify the failure. - If branch-related: patch code locally, commit, and push.
- If
process_review_commentis present, inspect surfaced review items and decide whether to address them. - If a review item is actionable and correct, patch code locally, commit, and push.
- If likely flaky/unrelated and
retry_failed_checksis present, rerun failed jobs with--retry-failed-now. - If both actionable review feedback and
retry_failed_checksare present, prioritize review feedback first — a new commit retriggers CI, so avoid rerunning flaky checks on the old SHA. - On every loop, verify mergeability / merge-conflict status (e.g. via
gh pr view). - After any push or rerun, immediately return to step 1 and continue polling on the updated SHA.
- If you paused
--watchto patch/commit/push, relaunch--watchyourself in the same turn after the push. - Repeat polling until the PR is green + review-clean + mergeable,
stop_pr_closedappears, or a user-help-required blocker is reached. - Keep consuming watcher output in the same turn while babysitting is active — do not end the turn with a detached
--watchprocess.
What ships with it
5 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.
- 3d ago First seen · 242 lines · 0 tokens per session scan A 7845ba6284b9
github-pr-sentinel is a skill published in the GitHub repository d-o-hub/github-template-ai-agents (2 stars, last pushed 3d ago), licensed MIT. It adds 89 tokens to every session and 2,522 once invoked, about $0.0004 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
git-flow-pr
Executes the full PR-driven development workflow: create an isolated feature branch from the current work, commit all staged changes, rebase cleanly onto the selected base branch (skipping any ancestor commits already merged), push the branch, and open a GitHub pull request linked to a related issue. Includes guidance…
memory-continuity
Preserves cross-session continuity with deterministic MEMORY.md, index.md, and snapshot handoffs under .agentic/memories/.
new-gh-issue-orchestration
Orchestrates a GitHub-issue-driven delivery workflow from issue intake to PR creation using reviewer-first then worker execution. Invoked when the user provides a GitHub issue link/number and asks to start end-to-end delivery.
git-worktree-workspaces
Sets up and uses Git worktrees for parallel task workspaces in the same repository clone, including safe cleanup of local worktrees. Invoked when the user asks to work on multiple branches at once, isolate tasks without extra clones, or create/remove worktrees.
client-approval
Draft a clean client approval request, set a 48h SLA with a 72h escalation, and track revision rounds so the third billable revision never slips through unbilled.
client-report
Turn a month of campaign data into a confident client report — executive summary, what worked, what didn't, next month's plan and a clean channel/KPI table with deltas.