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 hmj1026/dhpk --skill pr-summarygit clone --depth 1 https://github.com/hmj1026/dhpkWrote 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/hmj1026/dhpk/pr-summary)<a href="https://agentmods.dev/skills/hmj1026/dhpk/pr-summary"><img src="https://agentmods.dev/badge/skills/hmj1026/dhpk/pr-summary/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/hmj1026/dhpk/pr-summary"><img src="https://agentmods.dev/badge/skills/hmj1026/dhpk/pr-summary.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 | $0.00067 | $0.00510 |
| Opus 5.5 | $0.00027 | $0.00204 |
| Sonnet 5.5 | $0.00013 | $0.00102 |
| Haiku 4.5 | $0.00007 | $0.00051 |
Grade A, and why
pr-summary 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 yesterday.
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
PR Summary
Workflow
Run in the consumer repository and preserve --author <user> and
--label <label>. Resolve the repository with gh repo view, then query open
PRs with gh pr list --json ...; consume structured JSON rather than scraping
terminal formatting. Stop when gh is unavailable, the repository query
fails, or the PR query fails.
Filter bot-authored PRs, group the remaining records by ticket ID (including
stacked PR annotations), format the report, write the same report to
/tmp/pr-summary.md, and display it with copy instructions. The exact JSON
fields and grouping rules are in
references/workflow.md. This workflow never
changes GitHub state.
When NOT to Use
- A PR must be created, edited, merged, closed, or labeled.
- A code review or merge-readiness verdict is requested.
ghrepository credentials or access are unavailable.
Output
Formatted open-PR groups with ticket IDs and stacked-PR annotations, plus the
path /tmp/pr-summary.md and copy instructions. An empty result is a valid
report. Query or report-write failures are terminal UNAVAILABLE/FAIL
results and must be surfaced.
Verification
- Repository and PR data came from successful structured
ghJSON calls. -
--author/--labelfilters were preserved and bot PRs were handled. - Every included PR appears in exactly one ticket group (or an explicit
unassignedgroup). -
/tmp/pr-summary.mdexists and matches the displayed report.
References
references/workflow.md—ghfields, filters, bot exclusion, ticket grouping, and report format.
What ships with it
3 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.
- yesterday Changed · +2 lines 1f5f830d831c
- 23d ago First seen · 51 lines · 67 tokens per session scan A 3dce1943081c
pr-summary is a skill published in the GitHub repository hmj1026/dhpk (2 stars, last pushed today), licensed MIT. It adds 67 tokens to every session and 510 once invoked, about $0.0003 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 2026-09-24.
Other skills, from other repositories
catchup
Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.
backlog
Read, work, and maintain a Git repo's deferred-work items in docs/backlog/, one file per item. Use when the user says "backlog", "check backlog", "what's on my backlog", "work the backlog", "address the backlog", "add to backlog", "clean up backlog", or when a review or task produced items that are real but not being…
openspec-bulk-apply-change
Use when multiple active OpenSpec changes should be applied concurrently in isolated worktrees with delegated verification and no merge.
project-setup
Add a GitHub repository as a tracked project — creates workspace entity, installs workflow automation missions, and includes in dev brief scope.
apex-status
CTO-level project status from git and codebase state. Use when asked "where are we", "project status", "what's done", or at the start of a work session.
github-workflow
Install and operate a full GitHub issue-to-merge workflow for any repository using event-driven and cron missions. Handles issue planning, PR monitoring, CI fixing, staging review, and post-merge learning.