velocity.report: Skill for Claude Code

.claude/skills/plan-graduation/SKILL.md

plan-graduation is a skill for Claude Code from banshee-data/velocity.report. It costs 39 tokens per session (1,417 once invoked), scanned C, original, Apache-2.0.

A workflow for closing a completed implementation plan. It consolidates the plan into its permanent reference document and replaces the old plan file with a symbolic link, which is a filesystem pointer to another file.

In plain words
What is it for?
Use it after a plan is marked complete on the main branch to verify its canonical document, apply the required cleanup, or preview the cleanup with a dry run.
Why use it?
It prevents completed plans from becoming duplicate or conflicting documentation and enforces the rule that completion and cleanup happen in separate changes.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is banshee-data/velocity.report's own configuration. It tells Claude Code how to work on velocity.report itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything velocity.report configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is cd ../...

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/plan-graduation/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.

agentmods badge for plan-graduation

README.md
[![agentmods](https://agentmods.dev/badge/skills/banshee-data/velocity.report/plan-graduation/github.svg)](https://agentmods.dev/skills/banshee-data/velocity.report/plan-graduation)
Your own site
<a href="https://agentmods.dev/skills/banshee-data/velocity.report/plan-graduation"><img src="https://agentmods.dev/badge/skills/banshee-data/velocity.report/plan-graduation/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 plan-graduation

Your own site · 80×15
<a href="https://agentmods.dev/skills/banshee-data/velocity.report/plan-graduation"><img src="https://agentmods.dev/badge/skills/banshee-data/velocity.report/plan-graduation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,417 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00039 $0.01417
Opus 5.5 $0.00016 $0.00567
Sonnet 5.5 $0.00008 $0.00283
Haiku 4.5 $0.00004 $0.00142

Measured 1mo ago against content hash 99aa9e42b38a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

plan-graduation scanned grade C with 1 finding 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 1mo 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

- `- **Canonical:** [hub-doc.md](relative/path/to/hub-doc.md)` pointing to an existing hub doc <!-- link-ignore -->
.claude/skills/plan-graduation/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: plan-graduation

Graduate a completed plan into its canonical hub doc and replace the plan file with a symlink.

Usage

/plan-graduation docs/plans/my-plan.md
/plan-graduation docs/plans/my-plan.md --dry-run

Prerequisites

The plan file must already have:

  • - **Status:** Complete on main (merged, not just on a feature branch)
  • - **Canonical:** [hub-doc.md](relative/path/to/hub-doc.md) pointing to an existing hub doc

The two-PR rule is enforced by CI (make check-plan-hygiene, gate G10): a plan must be marked Complete on main before it can be replaced with a symlink. Never complete a plan and create its symlink on the same feature branch.

Procedure

1. Verify eligibility

# Confirm the plan is marked Complete on main
git show origin/main:<plan-path> | head -10

# Confirm it has a Canonical link
grep '^\- \*\*Canonical:\*\*' <plan-path>

If Status is not Complete on main, stop. The completion must land on main first in a separate PR.

2. Identify the canonical hub doc

Read the Canonical: metadata from the plan header. The target must be under one of these allowed hub prefixes:

Hub Scope
docs/lidar/ LiDAR pipeline, clustering, QC
docs/radar/ Radar pipeline, time-series
docs/ui/ Web frontend, macOS app, PDF generation
docs/platform/ Go packages, deploy, DB, tooling
config/ Config specifications
data/ Maths and data specifications

3. Consolidate content (if needed)

If the plan contains authoritative content not yet in the hub doc:

  1. Move or merge that content into the hub doc.
  2. Update the hub doc to reflect the final implementation state.
  3. Do not add a "Graduated plan:" link in the hub doc; graduated plan links add noise and point to symlinks that resolve back to the hub doc itself.

Read the full file on GitHub · 164 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.

  1. 1mo ago First seen · 164 lines · 39 tokens per session scan C 99aa9e42b38a

Subscribe to this mod's changes

plan-graduation is a skill published in the GitHub repository banshee-data/velocity.report (11 stars, last pushed today), licensed Apache-2.0. It adds 39 tokens to every session and 1,417 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-25.

Related

plan-graduation compared with skills from other repositories

plan-graduation next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
plan-graduationbanshee-data/velocity.reportSkill11todayApache-2.0C39Claude Code
analyzing-network-traffic-for-incidentsmukul975/Anthropic-Cybersecurity-SkillsSkill36k2mo agoApache-2.0A91Claude Code
analyzing-network-packets-with-scapymukul975/Anthropic-Cybersecurity-SkillsSkill36k2mo agoApache-2.0A75Claude Code
analyzing-network-traffic-with-wiresharkmukul975/Anthropic-Cybersecurity-SkillsSkill36k2mo agoApache-2.0B49Claude Code
whitebox-toolsznlgis/opengis-skillsSkill7610d agoMITA119Claude Code, Codex
performing-network-packet-capture-analysisxalgorix/xalgorixSkill1.3kyesterdayApache-2.0C62Claude Code, Codex
pdalznlgis/opengis-skillsSkill7610d agoMITB90Claude Code, Codex