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 agentmods add skills/saski/arnesto/code-notifynpx skills add saski/arnesto --skill code-notifygit clone --depth 1 https://github.com/saski/arnestoWhat 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 | $0.00054 | $0.00352 |
| Opus 5 | $0.00027 | $0.00176 |
| Sonnet 5 | $0.00011 | $0.00070 |
| Haiku 4.5 | $0.00005 | $0.00035 |
Grade A, and why
code-notify 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 yesterday.
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.
What it actually says
Code Notify
Goal
Make supported AI tools finish noisy terminal work with a local notification instead of requiring manual polling.
Use This Skill When
- The user asks to enable or wire completion notifications for an AI coding tool.
- A workflow should notify when a long-running task finishes or needs attention.
- You are documenting shared agent capabilities in a cross-tool setup.
Cross-Platform Rules
- Treat
code-notifyas an optional local dependency managed outside this repository. - Verify the installed command, wrapper, hook, or config before using it.
- Prefer shared wording and forward-slash paths so the guidance works across macOS, Linux, and Windows-compatible shells.
- Keep the integration additive. Do not replace existing hooks or notification settings unless the user asks.
Workflow
- Detect whether the current tool already has a notification hook or wrapper configured.
- Look for a local
code-notifycommand, alias, script, or documented install path before assuming invocation details. - If present, use it for end-of-task or attention-needed notifications only.
- If missing, tell the user the integration is unavailable in the current shell and continue without blocking the main task.
Output Guidance
- Mention that
code-notifyis available only after verifying the local installation. - Keep notification instructions tool-agnostic unless the user asks for a specific platform.
- Prefer concise setup notes over tool-specific prose duplication.
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.
- yesterday First seen · 37 lines · 54 tokens per session scan A 9d6abc86611e
code-notify is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed 6d ago), licensed Unlicense. It adds 54 tokens to every session and 352 once invoked, about $0.0003 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
pixir-delegate
Use Pixir as a headless subagent runtime from Claude Code or any harness with skill ! preprocessing (Codex roots and other no-hydration hosts use pixir-delegate-codex instead) — one-shot workers (pixir --json), parallel fan-out to N children (pixir delegate --spec), resumable steering (pixir resume), evidence…
pixir-delegate-codex
Use when a Codex CLI/Desktop root should fan out subagents, delegate to Pixir workers, run parallel workers, or manage a resident delegation daemon via Pixir Delegate; covers Codex preflight, AGENTS.md, approvals/sandbox, dry-run, daemon start/status/attach/cancel, closure evidence, and audited single-run execution…
pixir-diagnostics
Diagnose Pixir and T3 Code Pixir incidents from local canonical evidence. Use when a Pixir run, ACP/T3 thread, subagent/workflow, provider replay, or daily-driver dogfood session appears stuck, inconsistent, missing tool output, or hard to classify.
readonly-review
Run a no-network read-only review practice with two explorer steps and one synthesis step.
pixir-delegate-native
Delegate work to subagents from INSIDE a Pixir session using the native Subagent tools (spawnagent, waitagent, closeagent, listagents, sendinput) instead of shelling out to the pixir CLI. Use when you are a Pixir session that needs to fan out parallel workers, steer a child, or run skill-backed workflow templates …
repo-contracts-and-boundaries
Use when turning architecture, layering, ownership, dependency direction, schemas, structural metrics, quality thresholds, baselines, allowlists, or generated quality snapshots into repository checks.