agentmods.dev

foundation: Skill for Claude Code

.agents/skills/foundation-mcp/SKILL.md

foundation-mcp is a skill for Claude Code, Codex from dgraziosi/foundation. It costs 34 tokens per session (805 once invoked), scanned A, original, MIT.

A guide for choosing the right local vault MCP call, where MCP is the connection used to work with the vault. It maps common needs such as finding, reading, updating, linking, or reviewing records to the corresponding call.

In plain words
What is it for?
Use it when attaching a bot for the first time, finding a record, reading its activity, checking related work, updating it, or creating a link.
Why use it?
It prevents a bot from guessing which vault operation to use or relying on an outdated list of available calls.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is dgraziosi/foundation's own configuration. It tells Claude Code and Codex how to work on foundation itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything foundation configures →

not rated 1repo changed 3d ago A scan 34 tokens original MIT
View source ↗ dgraziosi/foundation
Reuse

Borrowing it

Nothing to install: this file belongs to dgraziosi/foundation. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dgraziosi/foundation/main/.agents/skills/foundation-mcp/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dgraziosi/foundation

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for foundation-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/dgraziosi/foundation/foundation-mcp.svg)](https://agentmods.dev/skills/dgraziosi/foundation/foundation-mcp)
Your own site
<a href="https://agentmods.dev/skills/dgraziosi/foundation/foundation-mcp"><img src="https://agentmods.dev/badge/skills/dgraziosi/foundation/foundation-mcp.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 805 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00034 $0.00805
Opus 5 $0.00017 $0.00402
Sonnet 5 $0.00007 $0.00161
Haiku 4.5 $0.00003 $0.00081

Measured 3d ago against content hash f22b4a7bd7ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

foundation-mcp 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 3d 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.

.agents/skills/foundation-mcp/SKILL.md · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Foundation MCP

This skill picks the vault call. It is not a tool list.

The user is the human who runs this vault on this machine. The vault MCP is on this machine (http://127.0.0.1:8787). Stay on localhost. Do not tell anyone to expose it.

Look up the live schema at call time (bootstrap, inspect_ontology, or the server tool list). Do not trust a dump in this file.

Which call

  • bootstrap — first attach / what tools and spine exist
  • lookup — a name, not a UUID yet
  • get — already have a UUID, need the record (not activity)
  • list_activity — already have a UUID, need the diary for that record (target). After a full page, send cursor. Read count. Omit fields and diff_only for the full snapshot. fields asks for a subset of activity keys. diff_only: true returns a lean before/after. Undo still uses the stored snapshot.
  • working_set — already have a UUID, need the open work around it. Depth, hard cap, and the spine-root due window read the vault settings row.
  • search — list or find without a bound id. After a full page, send cursor. Read count. search { url } finds a Gmail, Calendar, or Drive object. search { repo } finds a GitHub object. search { receipt } looks up a sent-mail or cleared-event receipt, then get. Same tool, not a new verb. due: today and overdue use the vault settings timezone (seed America/New_York). No settings tool.
  • upsert — write or patch a record; passing payload replaces that body. A bot writes data.receipt after send or clear. The server does not invent it. Changing type revalidates live incident edges and refuses if one would no longer be allowed (unlink first).
  • link — accept a suggested edge or hang a child. Suggestions and child_of placement read live kind, parent_types, and target_types, not a frozen slug list.
  • manage_relation — create or update a relation. System relations may edit source_types and target_types. Slug, kind, label, and symmetry stay locked.
  • delete — soft-delete a live node. Refuses when a live ref field still points at that id (clear the field first).
  • job — claim a named instance routine before a pass (dream, vault-health, activity-prune, …). Keep the token. A second live claim fails. finish records last run. release opens without recording. read is who and last run. Not a graph write and not get_vault_health. Activity prune itself is the host script scripts/activity-prune.sh.

Read the full file on GitHub · 33 lines

Changes

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.

  1. 3d ago Changed · +3 lines f22b4a7bd7ad
  2. 7d ago First seen · 30 lines · 34 tokens per session scan A 86491dd1b3dc

Subscribe to this mod's changes

foundation-mcp is a skill published in the GitHub repository dgraziosi/foundation (1 stars, last pushed 3d ago), licensed MIT. It adds 34 tokens to every session and 805 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 2026-08-31.

Building agents
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens