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 pjt222/agent-almanac --skill configure-mcp-servergit clone --depth 1 https://github.com/pjt222/agent-almanacWrote 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/pjt222/agent-almanac/configure-mcp-server)<a href="https://agentmods.dev/skills/pjt222/agent-almanac/configure-mcp-server"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/configure-mcp-server/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/pjt222/agent-almanac/configure-mcp-server"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/configure-mcp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 17 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium MCP Rug Pull · line 187 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 187 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00082 | $0.01892 |
| Opus 5.5 | $0.00033 | $0.00757 |
| Sonnet 5.5 | $0.00016 | $0.00378 |
| Haiku 4.5 | $0.00008 | $0.00189 |
Grade A, and why
configure-mcp-server 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 1mo 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configure MCP Server
Set up MCP server connections for Claude Code (WSL) and Claude Desktop (Windows).
When to Use
- Setting up Claude Code to connect to R via mcptools
- Configuring Claude Desktop with MCP servers
- Adding Hugging Face or other remote MCP servers
- Troubleshooting MCP connectivity between tools
Inputs
- Required: MCP server type (mcptools, Hugging Face, custom)
- Required: Client (Claude Code, Claude Desktop, or both)
- Optional: Authentication tokens
- Optional: Custom server implementation
Procedure
Step 1: Install MCP Server Packages
For R (mcptools):
install.packages("remotes")
remotes::install_github("posit-dev/mcptools")
For Hugging Face:
npm install -g mcp-remote
Got: mcptools installs from GitHub and loads in R without errors. mcp-remote is available globally via which mcp-remote or npm list -g mcp-remote.
If fail: For mcptools, ensure remotes is installed first. If GitHub rate-limits the install, set a GITHUB_PAT in ~/.Renviron. For mcp-remote, verify Node.js and npm are installed and on PATH.
Step 2: Configure Claude Code (WSL)
R mcptools server:
claude mcp add r-mcptools stdio \
"/mnt/c/Program Files/R/R-4.5.0/bin/Rscript.exe" \
-- -e "mcptools::mcp_server()"
Hugging Face server:
claude mcp add hf-mcp-server \
-e HF_TOKEN=your_token_here \
-- mcp-remote https://huggingface.co/mcp
Verify configuration:
claude mcp list
claude mcp get r-mcptools
Got: claude mcp list shows both r-mcptools and hf-mcp-server (or whichever servers were added). claude mcp get r-mcptools displays the correct command and arguments.
If fail: If the server does not appear in the list, verify ~/.claude.json contains the correct entry. If the claude command is not found, add it to PATH: export PATH="$HOME/.claude/local/node_modules/.bin:$PATH".
Step 3: Configure Claude Desktop (Windows)
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.
- 1mo ago First seen · 195 lines · 82 tokens per session scan A 2dd85ff4b36a
configure-mcp-server is a skill published in the GitHub repository pjt222/agent-almanac (42 stars, last pushed 5d ago), licensed MIT. It adds 82 tokens to every session and 1,892 once invoked, about $0.0003 per session on Opus 5.5. 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
audit-pr
Audit a whole PR against the delivery contract and return MERGE-READY or evidenced blockers with the full URL. Consumes the current review-change REVIEW-PASS receipt instead of re-running review axes; posts a SHA-bound ready comment; never edits or merges. Triggers: "audit-pr", "is this PR ready", "merge gate".
execute-phase
Step executor for units whose triage (unit-lane) decided which steps the unit needs. Implements one triaged step (or all remaining steps), with frozen acceptance, step-local gates, commits, red-gate repair, and diff-size guard. BREAKING: replaced PLAN.md/TASKS.md/progress.md/ACCEPTANCE.md with the unit doc's Tasks…
fold-findings
Repair persisted fix-now findings in compatible atomic batches: root-cause fixes, green gate, commit/push, and per-row folded: yes updates. Never reclassify or substitute backlog notes. Triggers: "fold-findings", "fix the review findings", "repair audit blockers".
init-workspace
Adapt the workflow scaffold to a new repository or add only missing substrate blocks to an existing install. Every install, hook, and overwrite needs explicit consent. Triggers: "init-workspace", "set up agentic workflow", "upgrade workflow scaffold".
product-audit
Audit the whole product across code, quality, process, docs, roadmap, and tooling; it owns the repo-wide bug hunt, security research, and broken-version investigation (scoped and budgeted per dimension, as distinct from review-change's change-scoped review). Persist one severity-ranked, F-numbered report with…
review-change
Review a change with only applicable internal axes, classify every finding, persist fix-now work, and return one evidence-backed decision. Findings only; --adversarial N uses isolated reviewers; --synthesize fuses supplied reviewer tables. Triggers: "review-change", "review this change", "adversarial review".