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 surajssd/dotfiles --skill pr-multi-agent-reviewgit clone --depth 1 https://github.com/surajssd/dotfilesWrote 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/surajssd/dotfiles/pr-multi-agent-review)<a href="https://agentmods.dev/skills/surajssd/dotfiles/pr-multi-agent-review"><img src="https://agentmods.dev/badge/skills/surajssd/dotfiles/pr-multi-agent-review.svg" alt="Measured on agentmods" 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 | $0.00191 | $0.04862 |
| Opus 5 | $0.00096 | $0.02431 |
| Sonnet 5 | $0.00038 | $0.00972 |
| Haiku 4.5 | $0.00019 | $0.00486 |
Grade D, and why
pr-multi-agent-review scanned grade D with 2 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 6d 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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
Read-only is enforced where the tool supports it (codex `--sandbox read-only`, claude `--permission-mode plan`, cursor `--plan`). **`opencode` and `agy` have no hard read-only switch** — `agy` runs with `--sandbox` (term Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Two distinct questions, answered separately: - Human docs: README / docs/ / user-facing .md updated where the change warrants it? - Agentic docs: CLAUDE.md / AGENTS.md / .github/copilot-instructions.md / GEMINI.md / How it starts
The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Multi-Agent Review
Run several AI coding CLIs as an independent review panel over the currently checked-out PR, then synthesize their reviews into one report. The value over a single reviewer is triangulation: a finding three tools independently flag is almost certainly real; a finding only one raises is either a sharp catch or a false positive — and the report should make that distinction visible so the user knows where to spend attention.
Nothing is posted to GitHub. Every artifact is a local file in a temp directory.
Requirements. git and at least one reviewer CLI are mandatory. gh + jq are needed for PR description and unresolved-thread context — without either, the skill degrades gracefully (diff + commits only) and says so. A timeout/gtimeout binary is used if present; otherwise a built-in bash watchdog enforces the per-reviewer timeout. The scripts avoid GNU-only flags (readlink -f, mktemp --suffix) so they run on stock macOS as well as Linux.
Trust boundary (read this). Two distinct exposures, because the panel feeds untrusted PR content — body, commit messages, third-party review comments, the diff — into the reviewer CLIs:
- Prompt-injection → tool execution. Two tools (
opencode,agy) run without a hard read-only sandbox —agywith its auto-approving--sandbox— so a malicious PR could attempt to drive them. Run this skill on PRs you trust, or isolate those tools (throwaway worktree, network off) when reviewing fork/contributor branches. - Data egress. Every reviewer streams the PR content to its model provider (Anthropic, OpenAI, GitHub, Google, …). If an external contributor pasted a secret into a PR body or comment, running the panel sends it to those third parties. Don't review PRs containing sensitive data you can't share with the reviewers' backends.
Step 5 covers the specifics.
The orchestrator (you) never reviews the code yourself. Your job is to gather context, dispatch the panel, and collate. If you inject your own opinions as if they were a reviewer's, you destroy the signal of how many independent tools agreed. You may reconcile and judge their findings during collation, but the findings must originate from the panel.
What ships with it
6 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.
- 6d ago First seen · 242 lines · 191 tokens per session scan D f39e37c83017
pr-multi-agent-review is a skill published in the GitHub repository surajssd/dotfiles (5 stars, last pushed today), licensed MIT. It adds 191 tokens to every session and 4,862 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it D with 2 findings (instruction-override phrasing, hidden instructions). 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.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.