wrap-phase

wrap-phase is a skill for Claude Code, Codex from Hadi99K/AGENT_SKILLS. It costs 24 tokens per session (395 once invoked), scanned A, original, MIT.

A development-phase closing procedure for projects that use AGENT_SYNC.md to record tasks, status, and handoffs.

In plain words
What is it for?
Summarising finished work, removing completed tasks, keeping only the latest handoff note, updating phase status, and committing and pushing the tracking file.
Why use it?
It turns scattered working notes into a clean handoff and marks the phase as complete.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions OpenCode.

Good fit Summarising finished work, removing completed tasks, keeping only the latest handoff note, updating phase status, and committing and pushing the tracking file.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hadi99k/agent_skills/wrap-phase
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 Hadi99K/AGENT_SKILLS --skill wrap-phase
Clone the repo
git clone --depth 1 https://github.com/Hadi99K/AGENT_SKILLS

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-phase

README.md
[![agentmods](https://agentmods.dev/badge/skills/hadi99k/agent_skills/wrap-phase.svg)](https://agentmods.dev/skills/hadi99k/agent_skills/wrap-phase)
Your own site
<a href="https://agentmods.dev/skills/hadi99k/agent_skills/wrap-phase"><img src="https://agentmods.dev/badge/skills/hadi99k/agent_skills/wrap-phase.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 395 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 $0.00024 $0.00395
Opus 5 $0.00012 $0.00198
Sonnet 5 $0.00005 $0.00079
Haiku 4.5 $0.00002 $0.00040

Measured 8d ago against content hash 2d3cdff8acf2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

wrap-phase 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 8d 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.

wrap-phase/SKILL.md · 33 lines

What it actually says

What I do

  • Read AGENT_SYNC.md to understand the completed work.
  • Add a Phase Summary highlighting everything built and key technical fixes.
  • Clean the Handoff Log by deleting all older conversations and keeping ONLY the single most recent log.
  • Clear completed tasks from the Session Task Board.
  • Update the Current Phase status to reflect completion.
  • Stage, commit, and push the AGENT_SYNC.md file automatically.

When to use me

Use this when the user asks to "wrap up the phase", "wrap the phase", or "clean up AGENT_SYNC".

Execution Steps

When invoked, execute the following steps without needing further confirmation:

  1. Analyze: Read AGENT_SYNC.md to grasp all recent sub-tasks and the handoff logs.
  2. Summarize: Create a clear ## 📖 Phase Summary: [Feature Name] section under the task board summarizing the accomplishments.
  3. Clean: Remove all [x] completed items from ## 📋 Session Task Board. Replace them with a note like "All completed."
  4. Purge: Delete all older handoff messages under ## 💬 Handoff & Discussion Log EXCEPT for the single most recent one.
  5. Update State: Change the "Current Phase" in the state section to indicate completion (e.g., "[Phase Name] Complete ✅").
  6. Save & Commit: Write the updated file to disk, then use bash to run: git add AGENT_SYNC.md && git commit -m "docs: wrap phase - clean agent sync and add phase summary" && git push
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. 8d ago First seen · 33 lines · 24 tokens per session scan A 2d3cdff8acf2

Subscribe to this mod's changes

wrap-phase is a skill published in the GitHub repository Hadi99K/AGENT_SKILLS (2 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 395 once invoked, about $0.0001 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.