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.
npx skills add nicodiansk/turbocharge --skill wrapgit clone --depth 1 https://github.com/nicodiansk/turbochargeWrote 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.
[](https://agentmods.dev/skills/nicodiansk/turbocharge/wrap)<a href="https://agentmods.dev/skills/nicodiansk/turbocharge/wrap"><img src="https://agentmods.dev/badge/skills/nicodiansk/turbocharge/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.
<a href="https://agentmods.dev/skills/nicodiansk/turbocharge/wrap"><img src="https://agentmods.dev/badge/skills/nicodiansk/turbocharge/wrap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00041 | $0.01308 |
| Opus 5 | $0.00020 | $0.00654 |
| Sonnet 5 | $0.00008 | $0.00262 |
| Haiku 4.5 | $0.00004 | $0.00131 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wrap Session
Capture session state for seamless resumption.
Announce: "Wrapping session — saving context for next time."
The Iron Law
NO SESSION END WITHOUT WRAP OFFER
When you detect a session is ending (goodbye, thanks, natural stopping point, context pressure), proactively offer to wrap.
What to Capture
1. Progress
- What was accomplished this session
- Which tasks/stories are complete
- Current branch, commit, state
2. Decisions
- Architectural choices made (with rationale)
- Approach decisions (with alternatives considered)
- User preferences discovered
3. Blockers & Open Questions
- What's stuck and why
- Questions that need answers
- Dependencies not yet resolved
4. Next Steps
- Prioritized list of what to do next
- Which skill to invoke first in next session
5. Resume Prompt
Generate a self-contained prompt the user can paste into a fresh session. Use @ references for files so Claude reads them automatically.
@CLAUDE.md @ATLAS.md @.claude/turbocharge-session.json Continue [PROJECT] - [CURRENT TASK]
Branch: `branch-name`
Completed:
- [completed items]
Next Task: [description]
1. [next task with context]
2. [following task]
Context Files:
- @path/to/design-doc.md (implementation plan)
- @path/to/relevant-code
Decisions to Remember:
- [key decision]: [rationale]
Start With:
/turbocharge:[skill] [args]
MANDATORY: @.claude/turbocharge-session.json MUST appear on the first line of every resume prompt — it is not optional context, it is the session state. Do not move it to "Context Files" or omit it.
5.5. Atlas + CodeMap Freshness (MANDATORY)
Before generating the resume prompt:
- Always run
/turbocharge:atlasto refresh the domain map — do not skip, even if changes seem minor. - If
.codemap/exists, runcodemap update(or note it in the resume prompt if watch mode is active).
Include in the resume prompt:
Navigation: @ATLAS.md is current. CodeMap index: run `codemap validate` if unsure.
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.
- 8d ago First seen · 148 lines · 41 tokens per session scan A bf31b88e6296
wrap is a skill published in the GitHub repository nicodiansk/turbocharge (2 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 1,308 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.
Other skills, from other repositories
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
mode-creator
Interactively create, install, activate, and verify custom claude-mem modes, including domain-specific observation types, concept tags, optional Telegram alerts, bot setup, worker restart, and startup-context verification. Use this whenever someone asks to customize what claude-mem remembers, create or change a mode…
cloud-sync
Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.
knowledge-agent
Build and query AI-powered knowledge bases from claude-mem observations. Use when users want to create focused "brains" from their observation history, ask questions about past work patterns, or compile expertise on specific topics.
claude-mem-install
Use this when setting up claude-mem on Cursor: local or remote worker, local host-login observer or remote cmem.ai inference.
how-it-works
Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks "how does claude-mem work?" or "what is this thing doing?".