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 hyperb1iss/hyperskills --skill super-good-prgit clone --depth 1 https://github.com/hyperb1iss/hyperskillsWrote 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/hyperb1iss/hyperskills/super-good-pr)<a href="https://agentmods.dev/skills/hyperb1iss/hyperskills/super-good-pr"><img src="https://agentmods.dev/badge/skills/hyperb1iss/hyperskills/super-good-pr/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/hyperb1iss/hyperskills/super-good-pr"><img src="https://agentmods.dev/badge/skills/hyperb1iss/hyperskills/super-good-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 67 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00071 | $0.03025 |
| Opus 5 | $0.00036 | $0.01512 |
| Sonnet 5 | $0.00014 | $0.00605 |
| Haiku 4.5 | $0.00007 | $0.00302 |
Grade A, and why
super-good-pr 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 2d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Super Good PR Descriptions
Give reviewers the context they need to evaluate the final change. Lead with the concrete problem and resulting behavior, explain the design choices that matter, and support validation claims with actual evidence. The body should work for someone who did not watch the session.
A small fix may need two paragraphs and validation. A migration may need ordering, compatibility, and rollout detail. Match the explanation to reviewer uncertainty; a long section checklist does not make a small PR more credible.
Establish the source of truth
Read the live PR body, title, base branch, head commit, and repository template before an update. Read the actual diff against that base; do not assume every PR targets main. For an existing PR:
gh pr view NUMBER --json title,body,baseRefName,headRefName,headRefOid,url
Fetch or refresh the relevant refs before deriving the local diff. A three-dot comparison uses the merge base and matches the usual PR comparison model. A stacked PR targets its preceding branch, so a diff against main would describe other layers too. GitHub documents these distinctions in its PR reference.
Gather the original requirement, final behavior, decisive files, and checks that actually ran. Separate observed evidence from expected behavior. Avoid universal claims such as "safe" or "fully covered" when the evidence establishes only a narrower property.
Make the title and opening carry the change
Name the behavior or design decision in the title. A reader scanning the PR list should distinguish this change from other work in the same subsystem. Prefer "Keep export retries attached to the original request" to "Improve export reliability." Follow the repository's title convention, including a Conventional Commit prefix when required; avoid packing internal symbols into the title at the expense of meaning.
Open with the situation that makes the change necessary and what the reader can expect afterward. Connect the mechanism to that result when it helps explain the fix. For a refactor, name the engineering constraint it removes and the behavior it preserves; do not invent a user-facing defect. These are relationships to explain, not three mandatory sentences or headings.
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.
- 2d ago Changed · +11 lines c5f3dac102b4
- 3d ago Changed · +19 lines · -91 tokens per session 065534e29cda
- 8d ago First seen · 139 lines · 162 tokens per session scan A 01572b01f6d9
super-good-pr is a skill published in the GitHub repository hyperb1iss/hyperskills (32 stars, last pushed 3d ago), licensed MIT. It adds 71 tokens to every session and 3,025 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 2026-08-30.
Other skills, from other repositories
agent-watchdog
Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a Codex session ID, Claude Code session/transcript, chat/thread link, PR, branch, log, or pasted run summary. Monitor until the other agent is done or blocked, reconstruct what the user asked, independently investigate the same…
comet-verify
Comet Phase 4: Verify and Close. Invoke with /comet-verify. Verify implementation matches design, handle development branch.
agent-design-best-practices
Best practices for designing Claude Code agent files (.claude/agents/.md). This skill should be used when writing or reviewing agent markdown files to ensure proper design with focused domains, correct tool access, reusable definitions, and separation of capabilities from lifecycle. Combines Anthropic's official…
graphify-dotnet
Use graphify-dotnet to generate codebase knowledge graphs, architecture snapshots, and exportable repository maps from .NET or polyglot source trees, with optional AI-enriched semantic relationships. USE FOR: graphify commands; graph JSON, HTML, SVG, Cypher, Markdown, and Obsidian exports; repository map and…
map-codebase
Deep architecture report that fans out parallel inspections across different aspects of the codebase (structure, tech stack, APIs, patterns, data flow, dependencies, testing) and synthesizes findings into a comprehensive document at .turbo/codebase-map.md and .turbo/codebase-map.html. Use when the user asks to "map…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…