agentmods.dev

wrap

An end-of-session command that records what happened during a coding session and prepares notes for the next one. It can also create a Git commit when requested.

In plain words
What is it for?
Use it to update priorities, handoff notes, daily logs, milestone records, and project wiki maintenance before closing the chat.
Why use it?
It reduces the chance of losing unfinished work, decisions, blockers, or verification evidence when a session ends.

Command

9 1mo ago A scan 30 tokens original MIT
View the source file valsecchi75/project-scaffolder
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 commands/valsecchi75/project-scaffolder/wrap
Clone the repo
git clone --depth 1 https://github.com/valsecchi75/project-scaffolder
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 476 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 $0.00030 $0.00476
Opus 5 $0.00015 $0.00238
Sonnet 5 $0.00006 $0.00095
Haiku 4.5 $0.00003 $0.00048

Measured 3d ago against content hash dab5bded297b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

commands/wrap.md · 41 lines

What it actually says

/wrap

End-of-session ritual. Run before closing the chat to preserve context for the next session.

Usage

/wrap
/wrap --commit

Steps

  1. Update wiki/priorities.md — mark completed tasks, adjust queue, record blockers
  2. Update wiki/handoff.md — what was done, what remains, which files the next session should read first
  3. Create/append daily-log/YYYY-MM-DD.md:
    • Tasks completed (with VERIFY evidence)
    • Decisions made (reference DEC-NNN)
    • Errors encountered (reference KE-NNN / ERR-NNN)
    • Approximate time
  4. Wiki hygiene pass (v3):
    • Update last-verified: YYYY-MM-DD in the frontmatter/header of every wiki page touched this session.
    • Flag (report only, no action) pages with last-verified older than 30 days: "N stale pages — consider /wiki-gc".
    • Check line caps: handoff.md ≤ 80, priorities.md ≤ 100, CLAUDE.md ≤ 120. If exceeded → move the overflow to wiki/_archive/YYYY-MM/ with a stub link (same protocol as /wiki-gc step 3).
  5. Update wiki/log.md if a phase-level milestone was reached
  6. Trigger Synapse Operation 4 (map hygiene): prune connections to deleted skills, trim "Recent Propagations" to last 20, flag orphan skills
  7. If --commit: stage modified files, generate commit message from completed tasks, create commit (never push)
  8. If context is near or above the threshold set in CLAUDE.md, run the Handoff Procedure from the context-manager skill (continuation prompt included)

Rules

  • Always produce a handoff, even for short sessions (minimum: "No progress, blockers: X").
  • Never skip the daily log.
  • --commit with mixed-intent work: ask for confirmation before committing.
  • Never force-push or touch remote.
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. 3d ago First seen · 41 lines · 30 tokens per session scan A dab5bded297b

Subscribe to this mod's changes

wrap is a command published in the GitHub repository valsecchi75/project-scaffolder (9 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 476 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.

CommitsGit and workflowMemory and context
Related

Other commands, from other repositories

speckit.git.commit

Auto-commit changes after a Spec Kit command completes.

unoplatform/uno · 10 tokens

commit-all

Group all changes semantically and commit each group separately.

samuelclay/NewsBlur · 10 tokens

commit

Based on the above changes, create a single git commit.

anthropics/claude-code · 4 tokens

commit

Safe git commit practices for MindRoom.

mindroom-ai/mindroom · 7 tokens

commit

智能生成 Git 提交信息并提交.

echoVic/blade-code · 8 tokens

commit

Create a Conventional Commit with signoff.

finos/git-proxy · 7 tokens