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 agentmods add skills/drvoss/everything-copilot-cli/sprint-retronpx skills add drvoss/everything-copilot-cli --skill sprint-retrogit clone --depth 1 https://github.com/drvoss/everything-copilot-cliWrote 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/drvoss/everything-copilot-cli/sprint-retro)<a href="https://agentmods.dev/skills/drvoss/everything-copilot-cli/sprint-retro"><img src="https://agentmods.dev/badge/skills/drvoss/everything-copilot-cli/sprint-retro.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.01674 |
| Opus 5 | $0.00019 | $0.00837 |
| Sonnet 5 | $0.00008 | $0.00335 |
| Haiku 4.5 | $0.00004 | $0.00167 |
Grade A, and why
sprint-retro 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 yesterday.
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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sprint Retrospective
Use Copilot CLI's /chronicle session history and git metrics to run a data-driven
retrospective. Go beyond "what went well / what didn't" — anchor the discussion in facts.
When to Use
- End of each sprint or iteration
- After a major feature ships
- When velocity has been unexpectedly high or low
- When the team wants to improve but isn't sure where to start
Getting Session Data
/chronicle — Session History
⚠️ Experimental feature — enable with
/experimental onbefore using.
/experimental on
/chronicle
/chronicle generates a timeline of your Copilot sessions: what you worked on,
session durations, tool usage patterns, and key decisions made.
Use this to answer:
- What did we actually build this sprint?
- How much time did each major task take?
- Which tasks got re-opened or took multiple sessions?
Git Metrics
> Analyze the git log for the last 2 weeks:
> - Number of commits
> - Files most frequently changed
> - Commit frequency by day (are we shipping continuously or in bursts?)
> - PR merge times (open → merged)
> - Any files with unusually high churn (changed in > 50% of commits)
# Commit count and velocity
git log --since="2 weeks ago" --oneline | wc -l
# Files with most churn
git log --since="2 weeks ago" --name-only --pretty=format: | sort | uniq -c | sort -rn | head -20
# PR cycle time (requires gh CLI)
gh pr list --state merged --json createdAt,mergedAt --limit 20
Retro Framework
What We Shipped
> Based on /chronicle and git log, summarize what we shipped this sprint.
> Group by feature area. Include: PR links, key decisions, and anything
> that surprised you about how it came together.
Velocity Analysis
> Compare planned scope vs. actual scope:
> - What was planned but not shipped? (Why?)
> - What was shipped but not planned? (Unplanned work or scope creep?)
> - What tasks took significantly longer than expected?
Friction Points
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.
- yesterday First seen · 214 lines · 39 tokens per session scan A fa305c6bfd78
sprint-retro is a skill published in the GitHub repository drvoss/everything-copilot-cli (45 stars, last pushed 8d ago), licensed MIT. It adds 39 tokens to every session and 1,674 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
speckit-workflow
Manage and run Spec Kit automation workflows via specify workflow. USE FOR: running a workflow by ID or local YAML, resuming a paused/failed run, checking run status, listing/installing/removing workflows, searching the workflow catalog, showing a workflow step graph. DO NOT USE FOR: extensions (use…
declare
Analyzes task plan and declares files that will be created or modified, producing declared-files.json.
execute
Executes the implementation plan for a Formic task.
launch-command
Launch orchestration and readiness assessment engine with cross-functional workstream tracking and go/no-go gates. Use when: launch readiness, launch checklist, launch orchestration, go no go, launch plan, are we ready to launch.
decompose
Decompose a feature spec into work items for orchestration via nw. Takes a PRD, phase doc, or verbal description and breaks it into human-reviewable PR-sized work items with dependencies mapped into batches. Use when asked to "decompose", "break down this feature", "create work items for", or "plan the work items".
friction-triage
Interactively walk through every friction log in .ninthwave/friction/ one at a time. For each log: read it, assess severity and possible duplicates, ask the human what to do (fix now / create work item / update doc / drop / merge / skip), execute the decision, and delete the log. This is the canonical way to clear the…