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 crisandrews/ClawCode --skill newgit clone --depth 1 https://github.com/crisandrews/ClawCodeWrote 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/crisandrews/clawcode/new)<a href="https://agentmods.dev/skills/crisandrews/clawcode/new"><img src="https://agentmods.dev/badge/skills/crisandrews/clawcode/new/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/crisandrews/clawcode/new"><img src="https://agentmods.dev/badge/skills/crisandrews/clawcode/new.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00054 | $0.00866 |
| Opus 5.5 | $0.00022 | $0.00346 |
| Sonnet 5.5 | $0.00011 | $0.00173 |
| Haiku 4.5 | $0.00005 | $0.00087 |
Grade A, and why
new scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/new — Start a new session
Save the current session to memory, then mark it as "reset pending" so the next message triggers a fresh greeting (like OpenClaw).
How this works (architecture)
OpenClaw's /new generates a new session ID and runs a greeting prompt on the next turn. In Claude Code, skills CANNOT invoke native /clear. Instead, we:
- Save the current session to
memory/YYYY-MM-DD.md - Write a marker
.session-reset-pendingwith the greeting prompt - Respond with a brief "new session" acknowledgement
- On the next message, the agent detects the marker, delivers the greeting, deletes the marker
This is the honest simulation of a session reset when native /clear is not invokable.
Steps
-
Detect surface (CLI vs messaging).
-
Summarize the current session to memory:
DATE=$(date +%Y-%m-%d) TIME=$(date +%H:%M)Append to
memory/$DATE.md:## Session summary (<TIME>) — before /new - <key point> - <key point> ### Open items - <pending>If the session was trivial, skip this step but still do the next one.
-
Write the reset marker:
cat > .session-reset-pending << 'EOF' A new session was started via /new or /reset. Greet the user in your configured persona, if one is provided. Be yourself - use your defined voice, mannerisms, and mood. Keep it to 1-3 sentences and ask what they want to do. If the runtime model differs from default_model in the system prompt, mention the default model. Do not mention internal steps, files, tools, or reasoning. EOF(This is the EXACT prompt from OpenClaw's session-reset-prompt.ts)
-
Respond briefly per surface:
CLI
🔄 New session started. Summary saved to memory/<DATE>.md.
Send a message to receive the welcome greeting.
(Or if you also want to clear the REPL context, run /clear afterward.)
🔄 *Session reset*. Send a message and I'll greet you again 👋
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.
- 1mo ago First seen · 96 lines · 54 tokens per session scan A 93151f54f960
new is a skill published in the GitHub repository crisandrews/ClawCode (64 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 866 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
alive-morning
Morning briefing -- read all walnut states, surface priorities, inbox count, stale walnuts, people nudges.
fresh-start
Continue in a new chat without losing anything — writes a compact handoff to paste into a fresh conversation. Use whenever the user wants to move to a new chat or conversation, hits usage limits, says replies got slow or Claude forgets earlier details, or the conversation has grown long.
token-check
Estimate how many tokens a pasted text, an attached file or the conversation so far takes, what it means for the context window and usage limits, and how to cut it. Use when the user asks how big something is in tokens, why they keep hitting limits, or whether a file is too large to send.
handoff
A session handoff tool that records important progress in a Markdown file and prepares a prompt for the next coding session. It preserves decisions, unfinished work, environment changes, and open questions.
ccc-resume-session
Load a saved session file from /.claude/sessions/ (latest, by date, or by path), read it fully, and brief project, state, what not to retry, blockers and next step before touching anything. Use when resuming work, continuing where you left off, or after a fresh session.
gut-sync
Use when a user resumes work and needs an orientation card without full human recall. Not for packaging context for another agent or session: use handoff. Never source or remote-system changes.