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/shivaedev/pardes/run-pr-cyclenpx skills add ShivaeDev/pardes --skill run-pr-cyclegit clone --depth 1 https://github.com/ShivaeDev/pardesWrote 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/shivaedev/pardes/run-pr-cycle)<a href="https://agentmods.dev/skills/shivaedev/pardes/run-pr-cycle"><img src="https://agentmods.dev/badge/skills/shivaedev/pardes/run-pr-cycle.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 | $0.00038 | $0.00746 |
| Opus 5 | $0.00019 | $0.00373 |
| Sonnet 5 | $0.00008 | $0.00149 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
run-pr-cycle scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run PR Cycle
Publish a verified owner-worker branch, hand the pull request to the user, and block until GitHub reports activity that needs attention.
Publish
- Check accepted commits, diffstat, verifier conclusions, and worker validation without reading the full diff.
- Use
write-pr-description. - Push the owner-worker branch and create or update the pull request with the
correct base branch and issue links.
- When using
gh, write the PR body to${CODEX_ARTIFACTS_DIR:-$HOME/codex-artifacts}/pr-bodies/codex-pr-body-<branch-slug>.md, pass it with--body-file <path>, and delete it immediately after GitHub accepts the pull request. Do not use a system temporary directory or the ignored.worktrees/directory. - Keep the host-executed
gh pr createcommand simple so persisted prefix approval can match it. Do not embed a multiline body with$'...', a heredoc, redirection, command substitution, or a pipeline.
- When using
- Open the pull request in the user's browser with
gh pr view --web <pr-url>. Run this outside the sandbox because it launches a host GUI. - Record the PR URL and waiting state in the workstream note.
The manager publishes. Workers commit but do not push. Never amend, force-push, or merge.
Wait
Run the monitor outside the sandbox from the outset because gh needs local
authentication and GitHub access:
uv run "<run-pr-cycle-skill>/scripts/watch_pr.py" <pr-url>
The helper always blocks until attention is required. Give the shell command a wait of at least 30 minutes when the tool supports a timeout. If the shell yields a running session, block on that process with long waits. Do not create a model-side polling loop.
When the helper returns, treat its JSON as an immediate notification. Read
attention, action_types, and observation before deciding what to do next.
observation: initial_snapshot means an actionable state was already present
when monitoring began; it does not mean the helper is still waiting.
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.
- 3d ago First seen · 76 lines · 38 tokens per session scan A 277b608f3f0d
run-pr-cycle is a skill published in the GitHub repository ShivaeDev/pardes (5 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 746 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…