wrap

wrap is a skill for Claude Code from Sprintra-io/sprintra-mcp. It costs 43 tokens per session (611 once invoked), scanned A, original, MIT.

A workflow for closing a coding session and saving its context, changed files, completed work, and project progress to Sprintra.

In plain words
What is it for?
It is used when work ends to review changes, update completed stories, save feature context, and close the work session.
Why use it?
It helps the next session resume with a record of what happened instead of reconstructing it from memory or chat history.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the sprintra plugin — 6 skills, 5 hooks shipped together

Good fit It is used when work ends to review changes, update completed stories, save feature context, and close the work session.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sprintra-io/sprintra-mcp/sprintra-wrap
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 Sprintra-io/sprintra-mcp --skill sprintra-wrap
Clone the repo
git clone --depth 1 https://github.com/Sprintra-io/sprintra-mcp

Made for: Claude Code.

Or install sprintra, the plugin that ships this one along with the rest of its 6 skills, 5 hooks.

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 wrap

README.md
[![agentmods](https://agentmods.dev/badge/skills/sprintra-io/sprintra-mcp/sprintra-wrap/github.svg)](https://agentmods.dev/skills/sprintra-io/sprintra-mcp/sprintra-wrap)
Your own site
<a href="https://agentmods.dev/skills/sprintra-io/sprintra-mcp/sprintra-wrap"><img src="https://agentmods.dev/badge/skills/sprintra-io/sprintra-mcp/sprintra-wrap/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 wrap

Your own site · 80×15
<a href="https://agentmods.dev/skills/sprintra-io/sprintra-mcp/sprintra-wrap"><img src="https://agentmods.dev/badge/skills/sprintra-io/sprintra-mcp/sprintra-wrap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 611 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.00611
Opus 5 $0.00022 $0.00305
Sonnet 5 $0.00009 $0.00122
Haiku 4.5 $0.00004 $0.00061

Measured 11d ago against content hash 4ccc30a80f2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

wrap 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 11d 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.

plugin/skills/sprintra-wrap/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wrap Up Session

Save the current coding session's context to Sprintra so the next session can resume seamlessly. This is the "save game" for development work.

Process

Step 1: Check Active Session

Call work_sessions(method: "get_active"). If no active session, skip to summary.

Step 2: Analyze What Happened

Look at:

  • Git status: what files were changed (use git diff --stat HEAD~5 via Bash if needed)
  • Conversation context: what stories were worked on, what decisions were made
  • Any stories that should be marked done

Step 3: Update Story Statuses

For any stories completed during this session:

stories(method: "update", story_id: "...", status: "done")

Add a comment to each completed story:

comments(method: "create", entity_type: "story", entity_id: "...", content: "Completed: [what was done, files changed, how tested]")

Step 4: Save Feature Context (if applicable)

If a feature was being worked on, save where you left off:

features(method: "save_context", feature_id: "...", where_left_off: "...", last_session_summary: "...", files_touched: [...])

Step 5: End Work Session

work_sessions(method: "end", summary: "...", files_changed: [...], stories_completed: [...], next_steps: "...")

Include:

  • summary: 1-2 sentences of what was accomplished
  • files_changed: key files modified (not every file — just the important ones)
  • stories_completed: IDs of stories marked done
  • next_steps: what to pick up next time (critical for session continuity)

Step 6: Git Sync (if commits were made)

git(method: "sync")

Then link commits to stories:

git(method: "link", story_id: "...", commit_hash: "...")

Step 7: Show Summary

## Session Wrapped ✓

Duration: [start time] → [now]
Stories completed: [list]
Files changed: [count]
Next steps: [what to do next time]

Context saved — next session will auto-resume.

Important

  • This should take <30 seconds. Don't over-analyze — capture the essentials.
  • If the user didn't work on any tracked stories, just end the session with a summary.
  • Always include next_steps — this is the most valuable field for session continuity.
  • Don't ask questions. Just gather, save, and confirm.

Read the full file on GitHub · 85 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. 11d ago First seen · 85 lines · 43 tokens per session scan A 4ccc30a80f2d

Subscribe to this mod's changes

wrap is a skill published in the GitHub repository Sprintra-io/sprintra-mcp (3 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 611 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 2026-08-31.