copilot-review-triage

copilot-review-triage is a skill for Claude Code from ivegamsft/basecoat. It costs 81 tokens per session (551 once invoked), scanned A, original, MIT.

A workflow for sorting automated Copilot pull-request review comments by their likely impact. A pull request is a proposed code change for review; the workflow records whether each suggestion is accepted, declined, resolved, or escalated.

In plain words
What is it for?
Use it to size review threads, validate small or bounded suggestions, record decisions, resolve safe items, and escalate broad, risky, or unclear findings.
Why use it?
It prevents review feedback from being silently ignored and avoids automatically applying or closing changes that may affect security, APIs, schemas, or deployments.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to size review threads, validate small or bounded suggestions, record decisions, resolve safe items, and escalate broad, risky, or unclear findings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ivegamsft/basecoat/copilot-review-triage
Install

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.

Any agent
npx skills add ivegamsft/basecoat --skill copilot-review-triage
Clone the repo
git clone --depth 1 https://github.com/ivegamsft/basecoat

Made for: Claude Code.

Wrote 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.

agentmods badge for copilot-review-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/ivegamsft/basecoat/copilot-review-triage/github.svg)](https://agentmods.dev/skills/ivegamsft/basecoat/copilot-review-triage)
Your own site
<a href="https://agentmods.dev/skills/ivegamsft/basecoat/copilot-review-triage"><img src="https://agentmods.dev/badge/skills/ivegamsft/basecoat/copilot-review-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.

agentmods 80×15 button for copilot-review-triage

Your own site · 80×15
<a href="https://agentmods.dev/skills/ivegamsft/basecoat/copilot-review-triage"><img src="https://agentmods.dev/badge/skills/ivegamsft/basecoat/copilot-review-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 551 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00081 $0.00551
Opus 5 $0.00041 $0.00275
Sonnet 5 $0.00016 $0.00110
Haiku 4.5 $0.00008 $0.00055

Measured 4d ago against content hash 91be47731e34, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

copilot-review-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.

skills/copilot-review-triage/SKILL.md · 64 lines

What it actually says

Copilot Review Triage

Process inbound Copilot review threads without silently discarding feedback. Read unresolved threads first. Never force-push or resolve before recording outcomes. Treat security, authorization, API, schema, and deployment-contract suggestions as Large unless a human scoped the change.

Impact Sizing

Size Signals Default disposition
Small Cosmetic, local, and behavior-preserving Apply if trivially correct; otherwise reply with a reason and resolve.
Medium Bounded edge case, refactor, validation, or test change Rubber-duck validate; apply if sound and in scope, otherwise decline with a reason and resolve.
Large Cross-cutting, security-sensitive, contractual, ambiguous, or scope-expanding Never auto-apply; summarize risk, escalate, and leave open.

Per-Thread Decision Loop

  1. Classify the suggestion and its acceptance impact.
  2. Apply or decline Small items with a recorded reason, then resolve.
  3. Rubber-duck validate Medium items; apply or decline with a reason, then resolve.
  4. Do not edit or resolve Large items; escalate its surface, risk, and decision.
  5. Batch accepted Small and Medium work into one focused commit.

Completion Gate

After applying a batch:

  1. Run relevant validation and a code-review risk pass.
  2. Reply with a commit SHA or decline reason.
  3. Auto-merge only if no Large items remain and required checks pass.

Recorded Decision Format

Use a reply that makes the disposition auditable:

Impact: Medium
Decision: Declined and resolved
Reason: The suggested validation duplicates the existing boundary check and
would not change the observable behavior.

For applied work, give the commit SHA and validation evidence. For Large work, state Decision: Escalated; left open.

Anti-Patterns

  • Silently ignoring a declined suggestion.
  • Auto-applying a Large item.
  • Evading required review-thread resolution.
Files

What ships with it

1 file 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.

Changes

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.

  1. 4d ago First seen · 64 lines · 81 tokens per session scan A 91be47731e34

Subscribe to this mod's changes

copilot-review-triage is a skill published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 551 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 2026-09-05.

Related

Other skills, from other repositories

review-implement-phase

Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.

prisma/orm · 38 tokens

engram-branch-pr

PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.

Gentleman-Programming/engram · 37 tokens

verify-behavior

Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…

nicknisi/dotfiles · 68 tokens

github-contributor

End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…

daymade/claude-code-skills · 133 tokens

revdiff

Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…

umputun/revdiff · 248 tokens

write-pr

Reference standards for writing pull request titles and descriptions in the tldraw repository, plus the pre-flight comment sweep over the diff. Use as supporting guidance when another skill or workflow needs PR content standards, not as the user-facing create/update PR workflow.

tldraw/tldraw · 53 tokens