A GitHub workflow skill that records what a merged version-one pull request changed so the behavior can be rebuilt or checked in version two.

Use it to create or reuse a detailed porting issue, link it to the original pull request, and give a version-two agent implementation guidance.

A rewrite does not automatically include fixes from the old codebase, so the behavior and acceptance conditions need a durable tracking issue.

pr-track-v1 — Skill for Claude Code and Codex by Kilo-Org/kilocode

About the project

Kilo Code is an open-source AI coding agent that works inside VS Code and JetBrains, from the command line, or through cloud services. Developers use it to build software with AI models, switch between providers, and run cloud agents or automated code reviews. The catalogue includes eleven skills, eight agents, and one instruction for Kilo Code.

Kilo-Org/kilocode · 27,627 stars · on GitHub · kilo.ai

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 Kilo-Org/kilocode --skill pr-track-v1

Clone the repo

git clone --depth 1 https://github.com/Kilo-Org/kilocode

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/kilo-org/kilocode/pr-track-v1/github.svg)](https://agentmods.dev/skills/kilo-org/kilocode/pr-track-v1)

Your own site

<a href="https://agentmods.dev/skills/kilo-org/kilocode/pr-track-v1"><img src="https://agentmods.dev/badge/skills/kilo-org/kilocode/pr-track-v1/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/kilo-org/kilocode/pr-track-v1"><img src="https://agentmods.dev/badge/skills/kilo-org/kilocode/pr-track-v1.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,107 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.

Model	Per session	Once invoked
Fable 5.1	$0.00072	$0.02107
Opus 5.5	$0.00029	$0.00843
Sonnet 5.5	$0.00014	$0.00421
Haiku 4.5	$0.00007	$0.00211

Measured today against content hash 8a0d9e001b13, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pr-track-v1 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.

.kilo/skills/pr-track-v1/SKILL.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Track V1 Change For V2

opencode v2 is a complete rewrite, so Kilo v1 fixes and features do not carry over automatically. This skill records what the behavior was and why it mattered in enough detail that a v2 agent can either confirm v2 already covers it or implement it from scratch without reading v1 code.

The /pr-track-v1 command is the normal entry point. Its arguments are optional context, not text to paste blindly into the issue.

Outcome

Finish with an issue in Kilo-Org/kilocode that:

Is titled [v2-port] <summary>, labeled core-v1-changes-port, and assigned to @me.
Opens with the auto-created provenance banner naming the source PR.
Describes the problem, the user-visible behavior contract, edge cases, and acceptance criteria — not a file-by-file diff narration.
Ends with a paste-ready Prompt For V2 Agent block.
Is linked back from a comment on the source v1 PR.
Contains no placeholders, invented motivations, or unverified claims.
Is reused rather than duplicated when a tracking issue for the same PR already exists.

Resolve The Source PR

Run gh auth status and confirm access.
Resolve the target repo explicitly on every gh call: pass --repo Kilo-Org/kilocode. The user may invoke this from a worktree or from another repository.
Arguments may contain PR numbers, PR URLs, or several of them. With no argument, resolve the current branch's PR and confirm it is the intended one:
```
gh pr view --repo Kilo-Org/kilocode --json number,url,title,state
```
Do not guess. If no PR can be resolved, ask for the PR number instead of inventing one.

Inspect The Change

Gather the behavior, not the implementation:

gh pr view <N> --repo Kilo-Org/kilocode \
  --json number,url,title,body,state,mergedAt,mergeCommit,author,labels,files,commits,comments,reviews,closingIssuesReferences
gh pr diff <N> --repo Kilo-Org/kilocode

Priority sources for functional detail, in order:

The PR body (problem / rationale / user-impact sections) and the changeset file in the diff. The changeset is written for end users and is the best one-line summary.
Tests added or changed in the diff. They state the behavior contract and the edge cases.
Linked issues (closingIssuesReferences) and review discussion. These hold the constraints and rejected alternatives that a rewrite is most likely to re-break.
The code diff, last, and only to extract intent: ordering, retries, defaults, platform quirks.

Read the full file on GitHub · 213 lines

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.

today First seen · 213 lines · 72 tokens per session scan A 8a0d9e001b13

Subscribe to this mod's changes

pr-track-v1 is a skill published in the GitHub repository Kilo-Org/kilocode (27,627 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 2,107 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-17.

Git and workflow ai-coding ai-developer-tools chatgpt claude vscode vscode-extension

pr-track-v1

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Track V1 Change For V2

Outcome

Resolve The Source PR

Inspect The Change

What this file has done since we first saw it

Other skills, from other repositories

launch

commit

gate

pair-loop

push

branch