Borrowing it
Nothing to install: this file belongs to amyodov/yet-another-agentic-chat. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/amyodov/yet-another-agentic-chat/main/.claude/skills/updating-mcp-tools/SKILL.mdgit clone --depth 1 https://github.com/amyodov/yet-another-agentic-chatWrote 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/amyodov/yet-another-agentic-chat/updating-mcp-tools)<a href="https://agentmods.dev/skills/amyodov/yet-another-agentic-chat/updating-mcp-tools"><img src="https://agentmods.dev/badge/skills/amyodov/yet-another-agentic-chat/updating-mcp-tools/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/amyodov/yet-another-agentic-chat/updating-mcp-tools"><img src="https://agentmods.dev/badge/skills/amyodov/yet-another-agentic-chat/updating-mcp-tools.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 | $0.00000 | $0.00673 |
| Opus 5 | $0.00000 | $0.00336 |
| Sonnet 5 | $0.00000 | $0.00135 |
| Haiku 4.5 | $0.00000 | $0.00067 |
Grade A, and why
updating-mcp-tools 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 11d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Updating the MCP tool surface
Two steps, in order: get the descriptions right, then sync the generated docs. The order matters because the docs are generated from the descriptions — polishing prose after regenerating means regenerating twice.
1. Description quality
The economics decide where words go: a tool description rides in every request while the server is connected, and a tool result is paid once per call. So:
- Permanent duties go in descriptions, tersely; situational nudges go in results. A sentence in a description is charged to every turn of every session that has the server installed, joined or not.
- Descriptions must carry the whole usage flow unaided — no client is obliged to surface server
instructions, and no skill is installed on the far side. The two flow-critical facts they must keep alive:
joining commits the model to polling
check_inboxevery turn, and a reply only ever arrives throughcheck_inbox. Weakening either turns a working radio into an apparently deaf one. - Dormant-visible tools (
list_channels,join_channel) are the whole context cost YAAC imposes on sessions that never join; be strictest about their length. - Parameter
Fielddescriptions are part of the surface too — a model fills arguments from them.
2. Sync the docs
docs/tools.md is generated, never hand-written. The generator imports yaac.frontend and reads the tool
registry itself — the same registration path that answers tools/list — so the file shows exactly what a
connected client sees: names, availability (dormant vs on-air), descriptions, parameter schemas, and the server
instructions. Editing it by hand would only create a version of the truth that the next regeneration deletes.
-
From the repository root, run:
uv run python ${CLAUDE_SKILL_DIR}/scripts/generate.py -
git diff docs/tools.mdand read the diff. It should contain precisely the change made in step 1 — an unexpected hunk means either the docs were stale (fine, that is the point) or the change had a wider blast radius than intended (worth telling the user about).
What ships with it
1 file 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.
- 11d ago First seen · 49 lines · 0 tokens per session scan A 56e7688715f3
updating-mcp-tools is a skill published in the GitHub repository amyodov/yet-another-agentic-chat (4 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 673 tokens. 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
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
choosing-swarm-patterns
Use when coordinating multiple AI agents with Agent Relay's workflow engine and need to pick the right orchestration pattern - covers the 10 core patterns (fan-out, pipeline, hub-spoke, consensus, mesh, handoff, cascade, dag, debate, hierarchical) plus 14 specialized ones, with decision framework and accurate…
deploying-to-staging-environment
Use when deploying changes to staging across relay, relay-dashboard, and relay-cloud repos - coordinates multi-repo branch syncing using git worktrees, automatically triggers staging deployments via GitHub Actions.
using-agent-relay
Use when you are a registered relay agent (a spawned worker, or a lead that called registeragent) coordinating with peers in real time over current Agent Relay MCP tools - messaging, channels, threads, reactions, search, inbox, actions, and worker spawn/release. For role selection and orchestrator startup…
review-fix-signoff-loop
Use when writing Agent Relay or Ricky workflows that must loop review, fix, and validation with fresh agent context until independent signoff agents, typically Claude and Codex, both agree the work is comprehensively complete. Covers fresh-context iterations, repairable gates, dual reviewer verdict contracts…
browser-testing-with-screenshots
Use when testing web applications with visual verification - automates Chrome browser interactions, element selection, and screenshot capture for confirming UI functionality.