Borrowing it
Nothing to install: this file belongs to juspay/neurolink. 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/juspay/neurolink/release/.claude/skills/neurolink-pr-merge/SKILL.mdgit 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/neurolink-pr-merge)<a href="https://agentmods.dev/skills/juspay/neurolink/neurolink-pr-merge"><img src="https://agentmods.dev/badge/skills/juspay/neurolink/neurolink-pr-merge/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/neurolink-pr-merge"><img src="https://agentmods.dev/badge/skills/juspay/neurolink/neurolink-pr-merge.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 | $0.00075 | $0.04749 |
| Opus 5.5 | $0.00030 | $0.01900 |
| Sonnet 5.5 | $0.00015 | $0.00950 |
| Haiku 4.5 | $0.00007 | $0.00475 |
Grade A, and why
neurolink-pr-merge 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 — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merging stacks and reading CI results
Moved out of the root CLAUDE.md. The required-status-checks table and the reset --soft incident stay in the root CLAUDE.md because CI files cite them by name. The generator, docs-site and advisory-gate playbooks are in the neurolink-ci-maintenance skill.
Stacked pull requests, and why they used to be unmergeable
A stacked pull request is one whose base is another feature branch rather
than release, opened so dependent work can proceed before its parent merges.
They work now. They did not before, and the reason is worth keeping because it
is invisible in exactly the way this repository keeps getting caught by.
Four of the five required status contexts — test, provider-safety-net,
security-suites, build-check — are jobs inside ci.yml. The fifth,
🔒 Single Commit Policy Validation, comes from a separate workflow,
single-commit-enforcement.yml. So a base-branch filter on ci.yml's
pull_request trigger does not decide whether those four checks pass. It
decides whether they are created at all. Scoped to branches: [release], a
stacked PR got none of those four, and a check that was never created reports as
missing, not as failing — which on a pull request is indistinguishable from
"still queued". PR #1670 sat at 1 of 5 required contexts from the day it was
opened, with nothing red to explain why.
single-commit-enforcement.yml broke them a second, independent way. Its
pull_request trigger was scoped to [release, main], so a stacked PR fell
through to the push-event path, which hardcoded BASE_BRANCH="origin/release".
Counting commits from release on a branch stacked on another feature branch
includes the parent's commit, so a single-commit PR was reported as carrying two
and failed a policy it had not broken.
Both pull_request triggers are now unfiltered by base branch. The
pull-request path already resolved the real base from github.base_ref; it was
simply never reached. The push path now asks for the branch's open PR and uses
its base, falling back to release when there is none.
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 Changed · +4 lines a2e64b9baa2b
- 4d ago First seen · 321 lines · 75 tokens per session scan A b319e7c860b9
neurolink-pr-merge is a skill published in the GitHub repository juspay/neurolink (168 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 4,749 once invoked, about $0.0003 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 2026-11-02.
neurolink-pr-merge compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| neurolink-pr-mergejuspay/neurolink | Skill | 168 | yesterday | MIT | A | 75 | Claude Code |
| resolve-publishomnigent-ai/omnigent | Skill | 11k | yesterday | Apache-2.0 | A | 21 | Claude Code, Codex |
| feature-publishomnigent-ai/omnigent | Skill | 11k | yesterday | Apache-2.0 | A | 24 | Claude Code, Codex |
| ci-commithumanlayer/humanlayer | Skill | 13k | yesterday | Apache-2.0 | A | 16 | Claude Code |
| pod-initSnowflake-Labs/cocoplus | Skill | 727 | 2d ago | MIT | A | 57 | Claude Code, Codex |
| lean-reviewSnowflake-Labs/cocoplus | Skill | 727 | 2d ago | MIT | A | 44 | Claude Code |
| map-diffSnowflake-Labs/cocoplus | Skill | 727 | 2d ago | MIT | A | 28 | Claude Code |