What is decision-review?

A skill for preparing an evidence-based report of unresolved decisions and passing confirmed answers through later review stages. It supports preparation, a voice or text discussion, and integration into the project.

It helps identify open decisions, prepare questions for discussion, record the answers, update dependent work, and prepare a pull request. The stages use different levels of reasoning for preparation, discussion, and integration.

Unresolved technical, research, schema, or project choices can block work or lead to inconsistent changes. This process records the questions and decisions in a Git packet, where Git is the version-control system used to track project changes.

How banshee-data/velocity.report configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to banshee-data/velocity.report. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/banshee-data/velocity.report/main/.claude/skills/decision-review/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/banshee-data/velocity.report

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/banshee-data/velocity.report/decision-review/github.svg)](https://agentmods.dev/skills/banshee-data/velocity.report/decision-review)

Your own site

<a href="https://agentmods.dev/skills/banshee-data/velocity.report/decision-review"><img src="https://agentmods.dev/badge/skills/banshee-data/velocity.report/decision-review/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/banshee-data/velocity.report/decision-review"><img src="https://agentmods.dev/badge/skills/banshee-data/velocity.report/decision-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,495 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	$0.00056	$0.03495
Opus 5.5	$0.00022	$0.01398
Sonnet 5.5	$0.00011	$0.00699
Haiku 4.5	$0.00006	$0.00349

Measured 15d ago against content hash 929911a1f1ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

decision-review 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 15d 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.

.claude/skills/decision-review/SKILL.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: decision-review

Turn unresolved questions into an organised report a person can discuss by voice, and carry their answers through review into the repository. The durable handoff is a decision packet in Git; chat memory is supplementary. This file is the canonical procedure for all three entry points.

Entry points and model handoff

Command	Phase	Model role
`/decision-review [scope or packet] [--minutes 20]`	Prepare or refresh the report	High capability, deep reasoning
`/decision-review-voice <packet>`	Discuss prepared questions and record decisions	Lightweight, voice capable
`/decision-review-integrate <packet>`	Evaluate answers, update dependencies, and prepare the PR	High capability, deep reasoning

Claude Code's entry points request opus, haiku, and opus respectively. These are client model selectors, not proof of which model ran. Other clients should read the named skill file and select equivalent capability tiers through their supported controls. Record the actual model when the host exposes it, otherwise unknown; record the requested tier separately. Do not invent a model switch, voice session, transcript, or background worker. A skill does not enable microphone access or schedule another run.

The default phase is prepare. When a phase wrapper reads this file, run that wrapper's phase only; do not recursively invoke another slash command. Use the active client's handoff mechanism when available and authorised. Otherwise save the packet and give the next invocation, packet path, branch, and requested model role to the user. If high capability is unavailable, leave a preparation or integration handoff pending rather than substituting lightweight technical review. If voice is unavailable, the same discussion can use text, with its modality recorded accurately.

Read the full file on GitHub · 233 lines

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.

references/packet-template.md 8.0 KB

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.

15d ago First seen · 233 lines · 56 tokens per session scan A 929911a1f1ba

Subscribe to this mod's changes

decision-review is a skill published in the GitHub repository banshee-data/velocity.report (11 stars, last pushed today), licensed Apache-2.0. It adds 56 tokens to every session and 3,495 once invoked, about $0.0002 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 2026-10-22.

Planning Research lidar radar road-safety street-safety traffic-analysis urban-analytics

decision-review next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
decision-reviewbanshee-data/velocity.report	Skill	11	today	Apache-2.0	A	56	Claude Code
analyzing-network-traffic-for-incidentsmukul975/Anthropic-Cybersecurity-Skills	Skill	36k	2mo ago	Apache-2.0	A	91	Claude Code
analyzing-network-packets-with-scapymukul975/Anthropic-Cybersecurity-Skills	Skill	36k	2mo ago	Apache-2.0	A	75	Claude Code
analyzing-network-traffic-with-wiresharkmukul975/Anthropic-Cybersecurity-Skills	Skill	36k	2mo ago	Apache-2.0	B	49	Claude Code
whitebox-toolsznlgis/opengis-skills	Skill	76	10d ago	MIT	A	119	Claude Code, Codex
performing-network-packet-capture-analysisxalgorix/xalgorix	Skill	1.3k	yesterday	Apache-2.0	C	62	Claude Code, Codex
pdalznlgis/opengis-skills	Skill	76	10d ago	MIT	B	90	Claude Code, Codex

velocity.report: Skill for Claude Code