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 juicesharp/rpiv-mono --skill pr-triagegit clone --depth 1 https://github.com/juicesharp/rpiv-monoWrote 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/juicesharp/rpiv-mono/pr-triage)<a href="https://agentmods.dev/skills/juicesharp/rpiv-mono/pr-triage"><img src="https://agentmods.dev/badge/skills/juicesharp/rpiv-mono/pr-triage/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/juicesharp/rpiv-mono/pr-triage"><img src="https://agentmods.dev/badge/skills/juicesharp/rpiv-mono/pr-triage.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 Excessive Agency · line 367 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00149 | $0.05761 |
| Opus 5 | $0.00075 | $0.02880 |
| Sonnet 5 | $0.00030 | $0.01152 |
| Haiku 4.5 | $0.00015 | $0.00576 |
Grade A, and why
pr-triage 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 12d 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 — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Triage
Size up a pull request before spending review effort: read the PR thread, compare
the diff against whatever standard the target repo carries, and emit a routing verdict.
Triage classifies and routes — it does not adjudicate line by line (that's
code-review, which the routed workflow runs). Read-only: no checkout, no mutation.
Stack-agnostic by design. The skill hard-codes no language, build tool, directory layout, or standards file — it discovers what the repo has and degrades to the code itself when nothing richer exists.
Input
$ARGUMENTS — a PR number (128), a PR URL, or empty (= the open PR of the current
branch). This value is substituted into the skill at render time; Step 1 reads it from
here directly — it is already the user's argument, not a raw token to re-parse.
Metadata
node "${SKILL_DIR}/../_shared/now.mjs"
echo
node "${SKILL_DIR}/../_shared/git-context.mjs"
PR resolution (ref normalisation, current-branch fallback, fuzzy disambiguation) is
LLM-invoked at Step 1 via the bundled _helpers/pr-fetch.mjs — it depends on the
substituted Input and on conversational clarification, which render-time substitution
cannot capture.
Flow
- Resolve + fetch PR → 2. Discover standards → 3. Dispatch assessment agents →
- Triage checkpoint → 5. Write artifact → 6. Present + recommend
Read-only contract (load-bearing): every agent is dispatched with read-only tools.
The skill MUST NOT git checkout, switch branches, or edit files — it reasons about the
PR diff as text fetched through gh. The security gate runs on fetched diff text
before any routed workflow touches the tree.
Steps
Step 1: Resolve the PR and Fetch the Thread
-
Read the substituted Input above and reduce it to a concrete spec the helper accepts — do not re-parse a raw token:
Input shape Pass to helper empty auto(helper resolves the current branch's PR)integer / #123/ a PR URLthe value verbatim prose / fuzzy ("the auth refactor PR") do NOT pass it. First run gh pr list --json number,title,headRefName,author, present candidates viaask_user_question(one question; options = candidate titles + "restate"), then pass the chosen number verbatim.
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.
- 12d ago First seen · 379 lines · 149 tokens per session scan A 4b98da22fdd5
pr-triage is a skill published in the GitHub repository juicesharp/rpiv-mono (779 stars, last pushed yesterday), licensed MIT. It adds 149 tokens to every session and 5,761 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
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.
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…