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 jxoesneon/Ciel --skill nanoclaw-replgit clone --depth 1 https://github.com/jxoesneon/CielWrote 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/jxoesneon/ciel/nanoclaw-repl)<a href="https://agentmods.dev/skills/jxoesneon/ciel/nanoclaw-repl"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/nanoclaw-repl/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/jxoesneon/ciel/nanoclaw-repl"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/nanoclaw-repl.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 | $0.00046 | $0.00856 |
| Opus 5 | $0.00023 | $0.00428 |
| Sonnet 5 | $0.00009 | $0.00171 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
nanoclaw-repl 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CIEL ADAPTATION: NanoClaw REPL (Session-Aware Subprocess REPL)
This skill provides operational guidance for NanoClaw v2, ECC's zero-dependency session-aware REPL built on claude -p subprocesses. It manages persistent markdown-backed sessions with branching, dynamic skill loading, and history compaction. Ciel's risk classifier gates subprocess spawning as mid→LLM_JUDGE.
Capabilities
- Persistent sessions: Markdown-backed session state survives across invocations.
- Model switching:
/modelcommand to change LLM model mid-session. - Dynamic skill loading:
/loadcommand to bring in skills on demand. - Session branching:
/branchto fork a session before high-risk changes. - Cross-session search:
/searchacross all stored sessions. - History compaction:
/compactto compress session history after major milestones. - Export:
/exportto md/json/txt for sharing or archival. - Session metrics:
/metricsfor token usage and session statistics.
Operating Guidance
- Keep sessions task-focused: One session per coherent task — avoid mixing concerns.
- Branch before high-risk changes: Use
/branchto preserve a rollback point before destructive operations. - Compact after major milestones: Run
/compactwhen a milestone is reached to free context budget. - Export before sharing: Use
/exportto create a portable artifact before handing off or archiving.
Extension Rules
- Zero external runtime dependencies: NanoClaw must remain dependency-free — all functionality is self-contained.
- Markdown-as-database compatibility: Session storage uses markdown files as the source of truth — never introduce a binary or external database.
- Deterministic command handlers: Each
/commandhandler must be deterministic and local — no network calls or non-reproducible side effects within handlers. - Preserve
claude -pcontract: All subprocess spawning goes throughclaude -p— do not introduce alternative invocation paths.
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 · 61 lines · 46 tokens per session scan A b649fe9c678a
nanoclaw-repl is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 46 tokens to every session and 856 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 2026-09-03.
Other skills, from other repositories
meeting-notes
OwnPilot official general skill for converting rough meeting notes, transcripts, and call summaries into decisions, action items, owners, risks, and follow-ups. Use when the user provides meeting content or asks for notes.
next-action
Use when the user wants a next-action recommendation based on current state — reads handoff/git/lessons/STATE and proposes top-3 by impact. Trigger: '/next', 'what should I do next', 'next action'. Proposes only, never executes.
agenticx-automation-crontask
Build and maintain Near Desktop scheduled (cron) tasks — default workspace /.agenticx/crontask, scheduletask tool, execution contract, and user-facing output. Use when the user wants recurring automation, crontab-style jobs, or to author/fix automation task prompts.
day-close
A day-ending protocol that reviews and records the required closing steps for the workday in IWE.
code-dev-workflow
Near codedev harness — Explore, Read, Author phases with outline-first context discipline.
lov-canonical-store
A central file and command-line workflow for maintaining one deduplicated vocabulary list as the source for other apps.