A procedure for closing a coding session by recording what happened in persistent project memory and updating the project’s sprint-status section. It then commits and pushes the changes, with safety checks handled by a script.

Use it at the end of a session to summarize work, save learnings in .agent-memory, update AGENTS.md, and commit and push the result.

It preserves useful context for later sessions and keeps the project status current. It also makes the end-of-session steps repeatable.

wrap — Skill for Claude Code and Codex by FuzzyKala: A procedure for closing a coding session by recording…

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/fuzzykala/cc-templates/wrap

Any agent

npx skills add FuzzyKala/cc-templates --skill wrap

Clone the repo

git clone --depth 1 https://github.com/FuzzyKala/cc-templates

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/fuzzykala/cc-templates/wrap.svg)](https://agentmods.dev/skills/fuzzykala/cc-templates/wrap)

Your own site

<a href="https://agentmods.dev/skills/fuzzykala/cc-templates/wrap"><img src="https://agentmods.dev/badge/skills/fuzzykala/cc-templates/wrap.svg" alt="Measured on agentmods" height="20"></a>

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,711 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.00055	$0.01711
Opus 5	$0.00028	$0.00856
Sonnet 5	$0.00011	$0.00342
Haiku 4.5	$0.00006	$0.00171

Measured 3d ago against content hash 133556e47bf5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

wrap scanned grade C with 1 finding 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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/wrap.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **Undo everything**: `git reset --hard <baseline>`. Remove orphan memory files if needed: `rm -rf .agent-memory/`.

.agents/skills/wrap/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/wrap — Session-end full recap

Wrap up a working session: distill what happened, codify learnings as persistent memory, update the AGENTS.md sprint-status block, then commit and push. Mechanical steps are handled by scripts/wrap.sh — deterministic bash with set -euo pipefail.

Assumed layout:

AGENTS.md at repo root with  and  markers. Sprint-status is 3-label: Last shipped / Next / Carry-forwards.
Each marker must appear exactly once as a complete line. Marker text inside explanatory prose does not count and must never bound replacement.
CLAUDE.md is a 1-line @AGENTS.md pointer. Never touch CLAUDE.md.
Memory persists at .agent-memory/<slug>.md with .agent-memory/INDEX.md as cross-reference. For Claude Code auto-load: ln -s .agent-memory ~/.claude/projects/<slug>/memory.

What NOT to do: (1) Do NOT propose new work, plan, or refactor — this is a session-end procedure. (2) Do NOT apply v2 rolling-window pattern — session history is in git log, not a separate file. (3) Do NOT touch CLAUDE.md — it stays a 1-line pointer. (4) Keep sprint-status block under 80 lines — Pre-ship and Deferred duplicate git log content.

Steps

Step 0: Pre-flight & Prep

Record baseline commit: git rev-parse HEAD. If anything goes wrong, git reset --hard <baseline> fully undoes the wrap.
If scripts/wrap-prep.sh exists, execute it to initialize the JSON context data bus:
```
npm run wrap:prep
```
Run the deterministic detection script:
```
N=$(bash ~/.agents/skills/wrap/scripts/wrap.sh pre-flight)
```
(Claude Code: also N=$(bash ${CLAUDE_SKILL_DIR}/scripts/wrap.sh pre-flight))
The script validates git availability, remote origin, sprint-status markers, detects last session N, checks idempotency, and initializes the context bus (path from $WRAP_CONTEXT_PATH, default /tmp/wrap-context.json). Prints the next session number to stdout.
If the script exits non-zero, halt and read the error message.
Store N for use in Steps 1 and 3.

Read the full file on GitHub · 109 lines

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.

scripts/wrap.sh 8.9 KB runs code

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.

3d ago First seen · 109 lines · 55 tokens per session scan C 133556e47bf5

Subscribe to this mod's changes

wrap is a skill published in the GitHub repository FuzzyKala/cc-templates (1 stars, last pushed 21d ago), licensed MIT. It adds 55 tokens to every session and 1,711 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Commits Git and workflow Memory and context ai-assistance automation claude-code development-workflow session-management templates

end

Close a work session — log what happened, update state and the decision log, propose durable memory updates, and check for uncommitted or unpushed work.

conorbronsdon/agent-workspace · 35 tokens

commit

Quick conventional commit with auto-staging and push, using project-specific scopes.

imadAttar/orbit · 0 tokens

prowler-commit

Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.

prowler-cloud/prowler · 33 tokens

git-commit

Generate well-formatted git commit messages following conventional commit standards.

ThinkInAIXYZ/deepchat · 15 tokens

contributing

How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…

HugoRCD/evlog · 68 tokens

commit-push-pr

Commit selected local changes, push the branch, and create or update a GitHub pull request with BitFun attribution. Use when the user asks to 提交 PR、提代码、commit and push、开 PR、create a pull request, or wants a Claude Code-like one-command PR publishing flow from BitFun.

GCWing/BitFun · 68 tokens

wrap