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 xonovex/platform --skill pull-request-guidegit clone --depth 1 https://github.com/xonovex/platformWrote 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/xonovex/platform/pull-request-guide)<a href="https://agentmods.dev/skills/xonovex/platform/pull-request-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/pull-request-guide/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/xonovex/platform/pull-request-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/pull-request-guide.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 | $0.00093 | $0.00886 |
| Opus 5.5 | $0.00037 | $0.00354 |
| Sonnet 5.5 | $0.00019 | $0.00177 |
| Haiku 4.5 | $0.00009 | $0.00089 |
Grade A, and why
pull-request-guide 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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pull Request Authoring Guidelines
How to write a pull request that gets reviewed fast and correctly. This skill owns the author's craft and returns the title and description inline during Create. Host creation, updates, and work-item links require a separate Publish operation with the git host's tooling; reviewer feedback lives in code-review-guide, and branch or commit work lives in git-guide.
Essentials
- One concern, kept small - one task per PR, aim 50-200 changed lines, see references/size-and-atomicity.md
- Lead with what / why / how - scope, the goal, the approach, up front, see references/description.md
- Show how you tested it - environment, edge cases, how to reproduce, see references/testing-evidence.md
- Surface tradeoffs early - state limitations and decisions before review, see references/tradeoffs.md
- Self-review before assigning - read your own diff, confirm CI is green, see references/self-review.md
- Use a lean template - 4-6 prompts, link related PRs and work items, see references/templates.md
Gotchas
- "Tested locally" tells the reviewer nothing - name the scenario, the environment, and how they can re-run it
- Line count measures volume, not risk - a 20-line auth change needs more scrutiny than a 400-line generated-code or scaffolding diff, so call those out
- A refactor bundled into a feature PR hides the real change - split it into its own PR
- A PR merges only on the required approving review(s) plus green required status checks (branch protection) - never bypass the gate
- Drafting a PR is not authorization to create or update one on a host
Example
A filled description for a small, focused change:
## What
Cache the resolved feature-flag set per request instead of re-reading it on every check.
## Why
PROJ-1234: the flag store was hit ~40x per request, adding ~15ms p95. Memoize it for the request scope.
## Changes
- Add a request-scoped FlagCache, resolve once in the entry middleware.
- Replace direct store reads in isEnabled() with the cache.
## Testing
- Unit: new FlagCache hit/miss/expiry tests.
- Manual: ran the planner flow locally, p95 dropped 210ms -> 195ms (logs attached).
## Tradeoffs / risks
- Flags changed mid-request are not picked up until the next request. Acceptable, flags do not change within a request.
## Related PRs
Part of the flag-perf set: !123, !124.
What ships with it
10 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 · 67 lines · 93 tokens per session scan A a3b51c6abf2f
pull-request-guide is a skill published in the GitHub repository xonovex/platform (6 stars, last pushed 2d ago), licensed MIT. It adds 93 tokens to every session and 886 once invoked, about $0.0004 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 2026-09-08.
Other skills, from other repositories
autofix-pr
Watch a pull request and fix it from a worktree of its own - CI failures, review feedback from trusted authors and merge conflicts are fixed, pushed to the PR branch and answered on the PR under the user's git and gh identity. Usage - /autofix-pr [ | ] [--once] [--every ] [--no-reply] [--yes] [instructions]…
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
hunk-release
Prepares, publishes, verifies, and curates Hunk releases. Use for release metadata, benchmarks, tags, publishing, release videos, backports, or recovery.
git
Git and code hosting platform management — GitHub, GitLab, Codeberg, Forgejo. Zero barrier — install x-cmd and manage repos from the terminal. Use for "git", "github", "gitlab", "repo", "pull request", "code hosting".
agent-debug-ci
Investigate failed scheduled or nightly GitHub Actions runs on the default branch, determine whether the failure is reproducible and repository-owned, implement the smallest evidence-backed fix, validate it, and open a pull request. Use when a failed nightly CI event starts an agent, or when the standard CI or…
doris-repo-review
Review an Apache Doris PR from a local clone with the same multi-agent, shared-ledger convergence workflow as the CI Code Review Runner. Use when the user supplies a PR to /doris-repo-review, asks to review a Doris PR locally, or asks for the CI-style review flow. Safely align only the current worktree to the exact PR…