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/bobbyjohnstx/tinycode/configure-notificationsnpx skills add bobbyjohnstx/tinycode --skill configure-notificationsgit clone --depth 1 https://github.com/bobbyjohnstx/tinycodeWhat 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 | $0.00017 | $0.04921 |
| Opus 5 | $0.00009 | $0.02461 |
| Sonnet 5 | $0.00003 | $0.00984 |
| Haiku 4.5 | $0.00002 | $0.00492 |
Grade B, and why
configure-notifications scanned grade B with 2 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 2d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
> **Security note:** Bot tokens, webhook URLs, and API keys are written in plaintext to `notifications-config.json`. Add this file to `.gitignore` in any repo where it may be committed, and restrict file permissions (`ch Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- The user wants to send a one-off notification right now — just run `curl` directly How it starts
The opening of the file, as written. The whole thing — 600 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configure Notifications
Set up notification integrations so you're alerted when tinycode sessions end, need input, or complete background tasks.
Security note: Bot tokens, webhook URLs, and API keys are written in plaintext to
notifications-config.json. Add this file to.gitignorein any repo where it may be committed, and restrict file permissions (chmod 600) if the host is shared.
When to Use
Use this skill when:
- The user says "configure notifications", "set up alerts", "notify me when the session finishes", or names a provider ("set up Telegram", "add Discord webhook", "Slack alerts")
- The user wants tinycode to send them a message on session-end, input-needed, or task-complete events
- The user wants to write a persistent notification integration to
notifications-config.json
When Not to Use
- The user wants to send a one-off notification right now — just run
curldirectly - The user wants to configure a Slack/Discord/Telegram bot for non-tinycode application logic (deploy alerts, CI notifications, etc.)
- The user wants to add an MCP server — use the
mcp-setupskill instead - The user is configuring tinycode settings, hooks, or permissions — use the
update-configskill
Output Contract
On successful configuration, always report:
- Provider configured (Telegram / Discord / Slack)
- Target (chat ID, channel name, or webhook host)
- Events enabled (from Step 6 selection)
- Config file path written to
- Test result (HTTP 2xx confirmed / skipped by user / failed — include error if failed)
Do not print a "Configured!" message if the test failed and the user did not explicitly skip testing.
Routing
Detect which provider the user wants based on their request or argument:
- If the trigger or argument contains "telegram" → follow the Telegram section
- If the trigger or argument contains "discord" → follow the Discord section
- If the trigger or argument contains "slack" → follow the Slack section
- If no provider is specified, use AskUserQuestion:
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.
- 2d ago First seen · 600 lines · 17 tokens per session scan B 36e8c9f1d4b4
configure-notifications is a skill published in the GitHub repository bobbyjohnstx/tinycode (11 stars, last pushed 4d ago), licensed MIT. It adds 17 tokens to every session and 4,921 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
system-prompts
Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.
tool-prompt-optimization
Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
archon-cli
Drive Archon through its CLI: run AI workflows on a repo, manage those runs (inspect, approve, reject, cancel, resume), set up Archon or change its config, author new workflows, and improve workflow prompts. Use when the user says "use archon", "run archon", "archon workflow", "fix issue #N with archon", "have archon…
semantic-compression
Re-encode verbose prose into a dense telegraphic register — punctuation as connectives, label frames, verbless assertions — without losing normativity or precision. Use when compressing system prompts, tool/function descriptions, skill bodies, or agent instructions; reducing token count or context bloat; making…
greet
A greeting skill for testing.