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 tomzx/agents --skill assess-pr-riskgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/assess-pr-risk)<a href="https://agentmods.dev/skills/tomzx/agents/assess-pr-risk"><img src="https://agentmods.dev/badge/skills/tomzx/agents/assess-pr-risk/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/tomzx/agents/assess-pr-risk"><img src="https://agentmods.dev/badge/skills/tomzx/agents/assess-pr-risk.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 | $0.00000 | $0.04192 |
| Opus 5.5 | $0.00000 | $0.01677 |
| Sonnet 5.5 | $0.00000 | $0.00838 |
| Haiku 4.5 | $0.00000 | $0.00419 |
Grade A, and why
assess-pr-risk 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 today.
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 — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assess PR Risk
Estimates how risky a pull request is and how confident that estimate is, then recommends the next action for a human reviewer.
Two axes: risk is a judgment about the change (how much damage if it is wrong, how hard to undo), and confidence is a judgment about the evidence base (what could and could not be verified).
The routing table turns the two scores into one next action, so the reviewer can decide at a glance.
This skill judges neither code craft (that is /review-pr), conformance (/verify-pr), nor product fit (/validate-pr); it runs alongside them in parallel, never reads their reports, and never revisits their verdicts.
Prerequisites
- Apply the shared SDLC conventions in
skills/sdlc/references/shared.md(PR Review Reports for report location and posting rules). - If no argument is provided, target the pull request from
$PR_NUMBER(and$REPO). ghCLI authenticated with read access to the target repositorygit worktreeavailable- Self-contained evidence: the assessment needs only the diff, the codebase, and churn of the touched files; it never reads or waits for sibling reports (
summarize-behavior-changes,adversarial-pr-review,analyze-test-coverage,validate-pr,verify-pr,review-pr) - Orchestrators (
review-pr-full,review-requested-prs) dispatch this skill concurrently with the analyze-test-coverage -> validate -> verify -> review chain and provideWORKTREE_DIR; because it shares no evidence with the chain, the parallel dispatch never weakens the estimate.
Skill attribution (GitHub)
Before posting to GitHub, read ../github-post-attribution/SKILL.md and append the footer for SKILL_DIR = assess-pr-risk.
Communication guidelines (outbound text)
Before composing any text posted or drafted on the user's behalf, apply communication-guidelines/SKILL.md.
Workflow
Fetch PR metadata + diff ($1)
|
v
CLOSED or MERGED? --> note and stop
|
v
Create git worktree on PR branch
|
v
Gather evidence
(diff, codebase, tests in the diff,
churn of touched files)
|
v
Score risk factors (8, each Low/Medium/High)
|
v
Score confidence (evidence-based rubric)
|
v
Route the next action (risk x confidence matrix)
|
v
Write assess-pr-risk.<sha>.md
Post if should-post-to-github allows
|
v
Clean up worktree
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.
- today Changed eabdc076702f
- 6d ago Changed · +11 lines 2bd1548fcff5
- 9d ago Changed · +8 lines b11b4626c8de
- 11d ago Changed · +1 lines 2bf2ebfb2c05
- 18d ago Changed 94f17c0c3e3d
- 21d ago Changed 2fa4e2f4d539
- 22d ago Changed · +26 lines aa832d96420b
- 25d ago Changed 71a2aca9a2b8
- 27d ago Changed · +1 lines cb98f45b2e6c
- 28d ago First seen · 279 lines · 0 tokens per session scan A 47785f613496
assess-pr-risk is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,192 tokens. 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 2026-09-22.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
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"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…