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 abrahamFerga/scrum-skills --skill sm-velocity-reviewgit clone --depth 1 https://github.com/abrahamFerga/scrum-skillsWrote 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/abrahamferga/scrum-skills/sm-velocity-review)<a href="https://agentmods.dev/skills/abrahamferga/scrum-skills/sm-velocity-review"><img src="https://agentmods.dev/badge/skills/abrahamferga/scrum-skills/sm-velocity-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.
<a href="https://agentmods.dev/skills/abrahamferga/scrum-skills/sm-velocity-review"><img src="https://agentmods.dev/badge/skills/abrahamferga/scrum-skills/sm-velocity-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00120 | $0.01726 |
| Opus 5 | $0.00060 | $0.00863 |
| Sonnet 5 | $0.00024 | $0.00345 |
| Haiku 4.5 | $0.00012 | $0.00173 |
Grade A, and why
sm-velocity-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Velocity Review
Purpose
Velocity is not a performance metric — it is a forecasting tool. A team with stable velocity can make reliable Sprint commitments and give stakeholders honest delivery timelines. A team with erratic velocity has a signal worth investigating: scope changes, underestimation, team instability, or interruptions. This skill surfaces the pattern so the Scrum Master and team can act on it.
Tool detection
- Check for active
mcp__azure-devops__*tools →$PM_TOOL = ado - Check for active
mcp__jira__*tools →$PM_TOOL = jira - If neither →
$PM_TOOL = manual
Step 1 — Collect Sprint history
Ask: "How many Sprints should I look back? The last 5–8 is typically enough to identify a meaningful trend."
Default: last 6 Sprints.
- ADO: use
work_list_team_iterationsto list recent iterations, thenwit_get_work_items_for_iterationfor each, filtering to Done/Closed state. Sum story points. - Jira: use sprint reporting tools to retrieve completed story points per sprint.
- Manual: ask "For each of the last [N] Sprints, provide: Sprint name/number, total story points committed, and total story points completed."
For each Sprint, record:
- Sprint name and dates
- Points committed at Sprint start
- Points completed (Done by Sprint end)
- Team size (if known — helps normalise for team changes)
- Any notable context: holidays, team member absence, unplanned work, scope additions mid-Sprint
Step 2 — Calculate the metrics
Average velocity:
Average = sum of completed points across all Sprints ÷ number of Sprints
Predictability rate (commitment accuracy):
Predictability = completed ÷ committed × 100, per Sprint
A rate consistently between 80–100% is healthy. Below 70% suggests chronic overcommitment. Above 110% suggests undercommitment or mid-Sprint scope additions.
Velocity trend: Compare the rolling average of the first half of the window to the second half.
- Improving: later Sprints average higher than earlier ones
- Declining: later Sprints average lower
- Stable: within ±15% across the window
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.
- 12d ago First seen · 160 lines · 120 tokens per session scan A e0c7c8a1a1ed
sm-velocity-review is a skill published in the GitHub repository abrahamFerga/scrum-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 120 tokens to every session and 1,726 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
turborepo
Skill "turborepo" from ashish7802/awesome-api-skills, covering turborepo skill, ecosystem graph preview, recommended next skills, quick start and production patterns.
github-project-management
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning.
github-project-management
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning.
github-project-management
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning.
devflow-planning
AI-powered sprint planning, velocity analysis, and capacity forecasting. Use for planning sprints, predicting outcomes, and providing agile recommendations based on historical data.
git-jira-integration
Integration between Git workflows and Jira issues. Generates branch names from issues, validates commit messages, and provides PR context from Jira specifications.