wrap

wrap is a skill for Claude Code, Codex from mag123c/toktrack. It costs 9 tokens per session (425 once invoked), scanned A, original, MIT.

A session-ending workflow for reviewing project changes, checking required documentation, reconciling the plan, and committing selected updates. A commit is a saved set of changes in Git, a system for tracking code versions.

In plain words
What is it for?
Use it to inspect Git status, check architecture and convention documents, record design decisions, review plan gates, and run the final actions selected by the user.
Why use it?
It reduces the chance of ending work with missing documentation, unresolved plan items, or unreviewed changes. It also makes the final state of the session explicit.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/mag123c/toktrack/wrap
Any agent
npx skills add mag123c/toktrack --skill wrap
Clone the repo
git clone --depth 1 https://github.com/mag123c/toktrack

Made for: Claude Code, Codex.

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/mag123c/toktrack/wrap.svg)](https://agentmods.dev/skills/mag123c/toktrack/wrap)
Your own site
<a href="https://agentmods.dev/skills/mag123c/toktrack/wrap"><img src="https://agentmods.dev/badge/skills/mag123c/toktrack/wrap.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 425 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00009 $0.00425
Opus 5 $0.00005 $0.00212
Sonnet 5 $0.00002 $0.00085
Haiku 4.5 $0.00001 $0.00042

Measured 5d ago against content hash 98934ea135e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 5d 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/wrap/SKILL.md · 57 lines

What it actually says

Wrap

Flow

Git Status → Doc Check → User Selection → Execute → Complete

Execution

  1. Git Status

    git status --short
    git diff --stat HEAD~3
    
  2. Doc Check Checklist (MUST)

    Change Target Required
    trait/type architecture.md on structural change
    convention conventions.md on new pattern
    Decisions .dev/DECISIONS.md on new feature/design

    DECISIONS.md entries (required check):

    • New feature implemented → record decision rationale, alternatives, reasons
    • Divergence between PLAN and actual implementation → add **Implementation Note**
    • New pattern/convention → also update conventions.md
  3. Plan Reconciliation (MUST)

    Reconcile the PLAN's provenance tags/gates ([unverified-gate]/[agent-inferred]/Phase 0) one-by-one — close (confirmed/falsified/changed) or explicitly delegate (delegated). No silent TODOs. Unsettled gates = wrap incomplete.

    Detailed procedure·delegated block·escalation criteria (WRAP=detail/DECISIONS=why/CLAUDE.md=critical·recurring) → references/reconciliation.md

  4. User Selection: AskUserQuestion

  5. Execute: Run selected items

DSL Rules (ai-context)

  • Table > prose
  • Codeblock > description
  • Core only, minimize lines

Commit

{type}({scope}): {summary}

Completion

wrap complete = skill chain finished Next task starts with new /clarify or /next

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.

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. 5d ago First seen · 57 lines · 9 tokens per session scan A 98934ea135e9

Subscribe to this mod's changes

wrap is a skill published in the GitHub repository mag123c/toktrack (188 stars, last pushed yesterday), licensed MIT. It adds 9 tokens to every session and 425 once invoked, about $0.0000 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 2026-08-30.

Related

Other skills, from other repositories

core-workflow

Detailed development workflow patterns, checklists, and standards. Auto-loads for complex tasks, planning, debugging, testing, or when explicit patterns are needed. Contains session protocols, git conventions, security checklists, testing strategy, and communication standards.

travisjneuman/.claude · 53 tokens

archive

Phase 10.5 — move the slug's workflow artifacts (intake, scout, research, spec, approvals, swarm state, security reports, rendered diagrams) to docs/archive/ / /. Runs before /commit so the committed tree is clean of work-in-flight files. workflow.json stays live and gets archived as the first step of /commit.

friedbotstudio/baseline · 77 tokens

commit

Workflow Phase 11 — Commit Preparation and Execution. Stages and commits the work. Requires /grant-commit first (Git Commit Guard enforces a 15-min ad-hoc consent window; inside a workflow the grant is slug-scoped and one grant covers the whole landing).

friedbotstudio/baseline · 59 tokens

commit-planner

Split a dirty working tree into single-concern Conventional Commits. The deterministic inventory.mjs helper groups dirty paths by concern (docs, source + paired test, config, governance); main context refines the grouping and presents a commit plan. Read-only until the user approves the plan — it never stages, never…

friedbotstudio/baseline · 0 tokens

git-workflow

Skill "git-workflow" from halflength-ampleness75/claude-code-recipes, covering git workflow, branch naming, rules, conventional commits and format.

halflength-ampleness75/claude-code-recipes · 0 tokens

capture

Harmonia capture stage - record learnings into the right memory tier, then ship structured commits. Use ONLY when explicitly invoked as /harmonia:capture.

foliveira/harmonia · 34 tokens