Borrowing it
Nothing to install: this file belongs to s-hiraoku/vscode-sidebar-terminal. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/s-hiraoku/vscode-sidebar-terminal/main/.claude/skills/pr-guardian/SKILL.mdgit clone --depth 1 https://github.com/s-hiraoku/vscode-sidebar-terminalWrote 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/s-hiraoku/vscode-sidebar-terminal/pr-guardian)<a href="https://agentmods.dev/skills/s-hiraoku/vscode-sidebar-terminal/pr-guardian"><img src="https://agentmods.dev/badge/skills/s-hiraoku/vscode-sidebar-terminal/pr-guardian/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/s-hiraoku/vscode-sidebar-terminal/pr-guardian"><img src="https://agentmods.dev/badge/skills/s-hiraoku/vscode-sidebar-terminal/pr-guardian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00157 | $0.01856 |
| Opus 5 | $0.00078 | $0.00928 |
| Sonnet 5 | $0.00031 | $0.00371 |
| Haiku 4.5 | $0.00016 | $0.00186 |
Grade A, and why
pr-guardian 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 10d 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Guardian
Watch a PR, detect problems, fix them, repeat — until everything is green.
Why this exists
After pushing a PR you typically wait for CI, check for merge conflicts, and respond to CodeRabbit review comments. Each issue requires a separate manual step. PR Guardian automates the entire feedback loop: it polls the PR status at a fixed interval, dispatches the appropriate fix skill when a problem is found, and exits only when all checks pass (or the iteration limit is reached).
Quick start
/pr-guardian # Default: 5 min interval, 20 max iterations
/pr-guardian --interval 3 # Poll every 3 minutes
/pr-guardian --max-iterations 10 # Give up after 10 cycles
Workflow
Step 0: Validate preconditions
Before starting the loop, verify:
ghCLI is installed and authenticated- Current branch has an open PR (
gh pr view) - Display the PR number and URL
If any check fails, report the error and stop.
Step 1: Poll PR status
Run the bundled status script:
bash <skill-path>/scripts/poll_pr_status.sh
This returns a JSON object with these fields:
| Field | Type | Meaning |
|---|---|---|
branch |
string | Current branch name |
pr_number |
int | PR number |
checks_total |
int | Total CI checks (excludes CodeRabbit) |
checks_passed |
int | CI checks that passed |
checks_failed |
int | CI checks that failed |
checks_running |
int | CI checks still in progress |
has_conflict |
bool | Merge conflicts detected |
coderabbit_check |
string | CodeRabbit check status: none/pending/pass/fail |
coderabbit_comments |
int | Number of CodeRabbit inline comments |
all_green |
bool | True when everything passes (including CodeRabbit) |
What ships with it
1 file 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.
- 10d ago First seen · 213 lines · 157 tokens per session scan A ba6ebbf18fc7
pr-guardian is a skill published in the GitHub repository s-hiraoku/vscode-sidebar-terminal (21 stars, last pushed 2d ago), licensed MIT. It adds 157 tokens to every session and 1,856 once invoked, about $0.0008 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 2026-09-01.
Other skills, from other repositories
github-release-management
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.
deployment-patterns
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up deployment infrastructure or planning releases.
agent-github-modes
Agent skill for github-modes - invoke with $agent-github-modes.
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.
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
atmos-hooks
Atmos hooks: lifecycle events, hook kinds, command/store/git/security hooks, step/steps hooks, when: conditions, scoping and overrides, toolchain integration, --skip-hooks, and Atmos Pro/local output.