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/dgraziosi/foundation/update-foundationnpx skills add dgraziosi/foundation --skill update-foundationgit clone --depth 1 https://github.com/dgraziosi/foundationWrote 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/dgraziosi/foundation/update-foundation)<a href="https://agentmods.dev/skills/dgraziosi/foundation/update-foundation"><img src="https://agentmods.dev/badge/skills/dgraziosi/foundation/update-foundation.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 | $0.00035 | $0.00625 |
| Opus 5 | $0.00017 | $0.00313 |
| Sonnet 5 | $0.00007 | $0.00125 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
update-foundation 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 4d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Foundation
You are applying product updates on the machine that runs this vault. The user can run this, or attach it to Vault Keeper.
Call bootstrap only if you need the current tools after the restart.
The user is the human who runs this vault on this machine. A vault is this running instance (FOUNDATION_DATA + Postgres). Do not call the graph “the Vault.” Life data stays in the vault, not in git.
Schedule and voice
Weekdays, late morning local time. If the clone is already up to date and /health is green, stay quiet. Ping the user when you pulled, restarted, failed, or stopped because a pull would risk stored data. If .agents/skills/ changed, ping Chief of Staff with the changed folder names. Do not stay quiet on a skill-only change.
User config (fill in)
- Foundation clone path: (the git checkout that
pnpm startuses) - MCP / health base: http://127.0.0.1:8787
- FOUNDATION_DATA: (from .env; default ./data)
Steps
- Record the current HEAD SHA (
git rev-parse HEAD). Do this before fetch or pull. After a pull you may also useORIG_HEAD. - In the Foundation clone:
git fetch origin. - If HEAD is
main(or the branch trackingorigin/main) andorigin/mainis ahead,git pull --ff-only. Fast-forward only. - If you pulled: restart the app (
pnpm start) so migrations run. No image rebuild. Wait until GET /health returns { ok: true, service: "foundation", db: "up" }. Then diff.agents/skills/against the SHA you recorded (orORIG_HEAD). If that tree changed, ping Chief of Staff with the changed folder names. Do not stay quiet on a skill-only change. A harness that points at.agents/skills/already sees those files. One tree. Do not copy.agents/skills/into a harness skill library. - If you did not pull and /health is green: stay quiet.
Stop and ping
- Working tree is dirty (other than ignored data like FOUNDATION_DATA / .env secrets). Stop and tell the user.
- HEAD is not main / not tracking origin/main. Stop and tell the user.
- Pull is not a fast-forward, would merge, or would conflict. Stop and tell the user.
- The next step would remove
FOUNDATION_DATAor delete the data folder. .envwould point the vault at a different leftover cluster.- Health does not come back after the app restart.
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.
- 4d ago First seen · 42 lines · 35 tokens per session scan A 486325e61e6e
update-foundation is a skill published in the GitHub repository dgraziosi/foundation (1 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 625 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…