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 EntityProcess/allagents --skill pr-interactive-reviewgit clone --depth 1 https://github.com/EntityProcess/allagentsWrote 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/entityprocess/allagents/pr-interactive-review)<a href="https://agentmods.dev/skills/entityprocess/allagents/pr-interactive-review"><img src="https://agentmods.dev/badge/skills/entityprocess/allagents/pr-interactive-review/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/entityprocess/allagents/pr-interactive-review"><img src="https://agentmods.dev/badge/skills/entityprocess/allagents/pr-interactive-review.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 Data Exfiltration · line 113 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00046 | $0.02727 |
| Opus 5 | $0.00023 | $0.01363 |
| Sonnet 5 | $0.00009 | $0.00545 |
| Haiku 4.5 | $0.00005 | $0.00273 |
Grade A, and why
pr-interactive-review scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS "http://127.0.0.1:<port>/api/comments?status=unanswered" How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interactive Pull Request Review
Use an existing review skill when one is available, and prefer its structured JSON output. This skill consumes structured findings and presents them locally; it does not select reviewer personas, assign severity, discover review scope, validate findings, or deduplicate findings.
Safety boundaries
- Accept a GitHub PR number or
https://github.com/<owner>/<repo>/pull/<number>URL. - Prefer the installed review skill's structured or agent output when it supports one. Do not parse markdown output.
- Store generated review data and comments outside the repository. The default workspace is
$XDG_STATE_HOME/allagents/pr-interactive-review/(or~/.local/state/allagents/pr-interactive-review/). - Never put tokens, cookies, GitHub authentication, comments, or generated review data in the repository.
- The server binds to
127.0.0.1by default. Non-loopback binding requires the explicit--exposeoption and emits a warning because findings and comments become network-visible. - Comments are local only. Do not post them to GitHub. This skill does not implement GitHub posting.
Obtain a structured review
From the repository that owns the PR, use an existing review skill when one is available. Ask it for structured JSON and pass the PR target directly. If no review skill is installed, use the host's available code-review capability and produce the same structured review artifact without inventing findings.
The review artifact must contain status, verdict, intent, scope.head_sha, and the validated findings array. Require status: complete; stop on failed, degraded, or skipped. Save the artifact outside the repository as review.json and consume that JSON directly. Do not scrape, transform, or infer findings from a human markdown report.
Concrete finding scenarios
After the review completes, actively enrich every finding without modifying review.json. For each stable #, inspect only its structured evidence and first_evidence plus the exact cited path at the reviewed commit. Write a separate JSON sidecar beside the review artifact (or in the external review workspace) as interactive-scenarios.json, keyed by the stable finding IDs:
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.
- yesterday Changed · +58 lines 39d1fda6acde
- 2d ago First seen · 130 lines · 46 tokens per session scan A fa6fe4ff0427
pr-interactive-review is a skill published in the GitHub repository EntityProcess/allagents (11 stars, last pushed 2d ago), licensed MIT. It adds 46 tokens to every session and 2,727 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.
Other skills, from other repositories
gsd-ship
Create PR, run review, and prepare for merge after verification passes.
gate-spec
Issue the binding pass or fail decision for a specification before planning begins. Use for “gate this spec”, “is this ready to plan?”, or “check this spec before implementation”.
gate
Independently verify an artifact against its criteria before it crosses a lifecycle boundary. Use for requirements, specs, plans, implementations, PRs, and explicit readiness checks.
audit-architecture
Check a spec against a persisted workspace architecture model, or build or refresh that model. Use for “does this fit the architecture?”, “audit against the arch model”, or “map this codebase architecture”.
pr
Draft or open a reviewer-ready pull request from verified work. Use when the user asks to create a PR or write its description; require confirmation before any remote action.
receive-feedback
Assemble a neutral evidence package for incoming PR feedback. Use when the user asks to understand, triage, or respond to review comments on their own pull request.