Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/adamdaw/claude-code-skills/pr-neighbors)<a href="https://agentmods.dev/skills/adamdaw/claude-code-skills/pr-neighbors"><img src="https://agentmods.dev/badge/skills/adamdaw/claude-code-skills/pr-neighbors/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/adamdaw/claude-code-skills/pr-neighbors"><img src="https://agentmods.dev/badge/skills/adamdaw/claude-code-skills/pr-neighbors.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 | $0.00105 | $0.02989 |
| Opus 5 | $0.00053 | $0.01494 |
| Sonnet 5 | $0.00021 | $0.00598 |
| Haiku 4.5 | $0.00011 | $0.00299 |
Grade A, and why
pr-neighbors scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR neighbours
Answers one question about a pull request: what else is moving in the code this PR touches? Not just PRs editing the same files — that is the easy half — but PRs editing code that calls into, or is called by, what this PR changed.
It reports. It does not rebase, comment, or change anything.
Why file overlap is not enough
A PR that changes a method and a PR that changes the only caller of that method share no files at all. They will merge cleanly and one of them will be wrong. Nothing in the GitHub UI shows this. That gap is the reason this skill exists, and it is why the graph layer is worth its cost.
Measured on a real pair: PR A changed OwnerShareReconciler, PR B changed
OwnerShareReconciliationBatch, which calls it. Zero shared files. Only the
graph found it.
Run it
python3 "${CLAUDE_PLUGIN_ROOT}/skills/pr-neighbors/scripts/pr_neighbors.py" <pr-number> \
--repo-path <local-checkout> [--index <gitnexus-index>] [options]
Four layers. The script runs 1–3 always; 4 is opt-in.
| Layer | Finds | Cost |
|---|---|---|
| 1 · File overlap | Other PRs editing a file this PR edits | free |
| 2 · Blast radius | Other PRs editing a file that calls, or is called by, a symbol this PR changed | needs a GitNexus index |
| 3 · Merged history | Already-merged PRs on the same ground, split by whether this branch has them | free |
4 · New references (--new-callers) |
Other PRs that add a reference to a blast-radius symbol | one API call per candidate |
Layer 4 exists because no graph can find it. If another PR adds the first-ever call to a method this PR is changing, that edge does not exist in any index — it lives only in the other PR's diff. It is off by default because it is the only slow layer; turn it on when the PR changes a shared or public API.
Measured on a 9,000-file repo: a 100-file / 90-symbol PR runs layers 1–3 in about 6s at depth 1 and 11s at depth 2. Layer 4 adds roughly a second per candidate PR it has not already reported (~45s across 40 open PRs).
What ships with it
2 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.
- 9d ago First seen · 237 lines · 105 tokens per session scan A c0cf9f0ffb02
pr-neighbors is a skill published in the GitHub repository adamdaw/claude-code-skills (2 stars, last pushed 20d ago), licensed MIT. It adds 105 tokens to every session and 2,989 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…