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 AcKeskin/contexture --skill pr-triagegit clone --depth 1 https://github.com/AcKeskin/contextureWrote 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/ackeskin/contexture/pr-triage)<a href="https://agentmods.dev/skills/ackeskin/contexture/pr-triage"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/pr-triage.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 | $0.00075 | $0.02674 |
| Opus 5 | $0.00037 | $0.01337 |
| Sonnet 5 | $0.00015 | $0.00535 |
| Haiku 4.5 | $0.00007 | $0.00267 |
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 4d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pr-triage
Reviewee-side triage of PR review feedback. A sibling of the GitHub reviewee organs pre-push and pr-author; the reviewer side is pr-review.
This skill does not respond to reviewers. You write every reply yourself, every time — pr-triage never drafts reply text and never posts. What it does is turn a pile of unresolved comments into a worked checklist and drive the code actions the comments call for: it fetches the unresolved comments, lays them out as a themed checklist, and walks each one with you to a decision. When a comment needs a code change, pr-triage routes that change to /dispatch or /orchestrate rather than editing inline — so independent fixes fan out in parallel and cross-cutting ones decompose properly.
The output is code changes, not replies. Replies are entirely yours.
GitHub boundary — read-only. The only GitHub call pr-triage makes is the read-only fetch of comments. It never runs gh pr comment, never posts a thread reply, never resolves a thread, and — unlike its predecessor — never even drafts reply text. Resolution is the reviewer's signal; the reply wording is yours.
Manual trigger via this description (per skill-auto-fire). It does not auto-fire — you invoke it when you want to work a PR's comments.
When to run
- The user types
/pr-triageor/pr-triage <PR>. - The user says "work through the PR comments", "triage the review feedback", "let's go through what they flagged", or equivalent — and wants to act on the comments, not have replies drafted.
Skip when:
- The user directs a single comment ("just fix comment #3", "only the null-check one"). Back off — no checklist ceremony; do the one thing.
Does not auto-fire. No hook, no session-start trigger, no fire-on-reading-comments. Manual only.
Inputs
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.
- 4d ago First seen · 157 lines · 75 tokens per session scan A 08e557a26449
pr-triage is a skill published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 2,674 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
OCR Review-to-Approval Loop
Drive a PR to an approved code review by looping OCR's multi-agent review and address steps. Runs /ocr:review then /ocr:address repeatedly until the review verdict is APPROVE, then one final /ocr:address for leftover suggestions, posting every review and every address round to the GitHub PR as comments. Use when the…
audit-pr
Audit a whole PR against the delivery contract and return MERGE-READY or evidenced blockers with the full URL. Consumes the current review-change REVIEW-PASS receipt instead of re-running review axes; posts a SHA-bound ready comment; never edits or merges. Triggers: "audit-pr", "is this PR ready", "merge gate".
hunk-release
Prepares, publishes, verifies, and curates Hunk releases. Use for release metadata, benchmarks, tags, publishing, release videos, backports, or recovery.
github-review-pr
Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents. Use this skill whenever the user wants to review a PR, asks for code review on a pull request, mentions "review PR", "check this PR", "look at pull request", or references a PR number or GitHub PR URL. Do NOT use for…
pr-triage
First-touch triage for external pull requests - verdict, label, and a welcoming comment within minutes of open.
lean-review
CocoLean diff-scoped over-engineering audit — scans uncommitted git diff and applies five classification tags (delete/stdlib/native/yagni/shrink) to identify unnecessary surface area before commit.