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 juspay/neurolink --skill github-commentinggit clone --depth 1 https://github.com/juspay/neurolinkWrote 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/juspay/neurolink/github-commenting)<a href="https://agentmods.dev/skills/juspay/neurolink/github-commenting"><img src="https://agentmods.dev/badge/skills/juspay/neurolink/github-commenting/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/juspay/neurolink/github-commenting"><img src="https://agentmods.dev/badge/skills/juspay/neurolink/github-commenting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Prompt Injection · line 11 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00041 | $0.00631 |
| Opus 5.5 | $0.00016 | $0.00252 |
| Sonnet 5.5 | $0.00008 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
github-commenting 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean GitHub PR commenting
Before posting anything
- List the existing review comments AND issue comments on the pull request first.
- Every comment you post starts with an invisible marker line:
<!-- yama:<stable-finding-id> -->. If a marker for the same finding already exists, do NOT post it again — update that comment if it needs fixing, otherwise leave it alone.
Inline comments
- Anchor to the exact file and line in the DIFF. A line that is not part of the diff cannot hold a comment — anchor to the nearest changed line and say so.
- Multi-line ranges:
start_lineis the first line,lineis the last;side/start_sideareRIGHTfor added lines andLEFTfor deleted ones. - Tool shapes differ: some GitHub MCP servers post an inline comment in one call; the hosted server may require the pending-review lifecycle (create review → add comments → submit). If a pending review is opened it MUST be submitted — both or neither, never half.
Suggestion blocks — a fix the author applies in one click
Explain the issue in one or two sentences ABOVE the block, then:
```suggestion
the replacement for the entire anchored line range
```
- The block's body replaces the WHOLE
start_line..linerange — include every line of the range, exactly indented. - If the replacement itself contains triple backticks (markdown files, code fences), use a four-backtick outer fence (
````suggestion) so GitHub does not close the block early. - Prefer a suggestion block whenever you propose a concrete code fix - it is the fix the author applies in one click, and an inline comment about a code change should normally carry one. Fall back to prose only when the right code is genuinely uncertain.
Formatting for humans
- One finding per comment: severity (CRITICAL / MAJOR / MINOR), what breaks, why it matters here, and the fix.
- Cite rulebook ids where they apply.
- Evidence longer than ~10 lines goes in a collapsible section:
<details><summary>evidence</summary>…</details>. - Prefer short headers, tables and task lists over walls of prose. No emoji noise.
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 · 49 lines · 41 tokens per session scan A 7e7ac9d3dbaa
github-commenting is a skill published in the GitHub repository juspay/neurolink (157 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 631 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
feature-publish
Commit the feature, write the PR body, publish in the selected mode, and drive the PR.
lean-review
CocoLean diff-scoped over-engineering audit — scans uncommitted git diff and applies five classification tags (delete/stdlib/native/yagni/shrink) to identify unnecessary surface area before commit.
gh-address-comments
This skill should be used when addressing GitHub pull request review comments systematically with mandatory resolution tracking. Use when user says "address PR comments", "fix review feedback", "handle PR review", "resolve PR threads", or needs to ensure all review comments are addressed before merging. Fetches…
resolve-publish
Commit the validated fix and follow local-only, workflow-owned, or direct PR publication.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
resolve-drive-pr
Drive an open PR through Polly/OCR, validation, and maintainer handoff.