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 kaivyy/kabot --skill config-managergit clone --depth 1 https://github.com/kaivyy/kabotWrote 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/kaivyy/kabot/config-manager)<a href="https://agentmods.dev/skills/kaivyy/kabot/config-manager"><img src="https://agentmods.dev/badge/skills/kaivyy/kabot/config-manager.svg" alt="Measured on agentmods" 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 | $0.00819 |
| Opus 5 | $0.00020 | $0.00409 |
| Sonnet 5 | $0.00008 | $0.00164 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
config-manager 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Config Manager
Use this skill when the user asks whether a Kabot setting is enabled, why a config value is not taking effect, why a model/provider/channel setup is failing, or asks you to safely edit Kabot config after reviewing the current state.
Use this skill for
~/.kabot/config.json,config.json.bak, ormode_config.json- model/provider/memory/backend settings
- channel settings such as WhatsApp, Telegram, Discord, accounts, allowlists, pairing, or login-related config
- conflicting top-level vs per-account config
- invalid JSON, missing keys, missing env-backed settings, or wrong defaults
- runtime issues where the next grounded step is to inspect config, status output, or logs before changing anything
Grounding rules
- Read the real config first. Do not guess from defaults.
- When the issue is runtime behavior, inspect the relevant status output and logs before proposing a fix.
- Separate explicit config from code fallback/default behavior. Say which is which.
- Prefer the smallest safe config change that resolves the issue.
- Ask for approval before any state-changing edit, restart, reload, relink, or destructive cleanup.
Files and evidence to inspect
~/.kabot/config.json~/.kabot/config.json.bak~/.kabot/mode_config.json~/.kabot/logs/- relevant workspace docs/bootstrap files if the user references them
- relevant runtime status output if available
Workflow
- Ground the request in real evidence
- Identify the exact setting, subsystem, or symptom the user cares about.
- Read only the relevant config sections first.
- If the user asks "is X configured?", answer from the file, not from assumption.
- If the issue is a runtime error, compare config with the latest relevant log/status evidence.
- Diagnose before editing
- Quote the current relevant values briefly.
- Call out missing keys, conflicting overrides, duplicated account blocks, malformed JSON, or env/config gaps.
- If the value is not explicitly set, say whether Kabot is falling back to a code default and where that default comes from.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 91 lines · 41 tokens per session scan A 85f8928469d0
config-manager is a skill published in the GitHub repository kaivyy/kabot (20 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 819 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 2026-08-30.
Other skills, from other repositories
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
triage-issue
Analyze a GitHub issue, verify claims against the codebase, and close invalid issues with a technical response.
hive.error-recovery
Follow a structured recovery decision tree when tool calls fail instead of blindly retrying or giving up.
technology-search
Search tech blogs, developer forums, and IT media (TechCrunch, Hacker News, 36氪, etc.) for software and hardware industry updates with heat ranking and EN↔CN translation. Use this skill only when the topic is clearly about programming, software, hardware, AI, or IT infrastructure.
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.
imap-smtp-email
Read and send email via IMAP/SMTP. Check for new/unread messages, fetch content, search mailboxes, mark as read/unread, and send emails with attachments. Works with any IMAP/SMTP server including Gmail, Outlook, 163.com, vip.163.com, 126.com, vip.126.com, 188.com, and vip.188.com.