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.
curl -O https://raw.githubusercontent.com/dgraziosi/foundation/main/.agents/skills/drift-read/SKILL.mdgit 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/drift-read)<a href="https://agentmods.dev/skills/dgraziosi/foundation/drift-read"><img src="https://agentmods.dev/badge/skills/dgraziosi/foundation/drift-read.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 | $0.00000 | $0.00494 |
| Opus 5 | $0.00000 | $0.00247 |
| Sonnet 5 | $0.00000 | $0.00099 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
drift-read 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 2d 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.
What it actually says
Drift read
You are running a report-only look at the graph. The user can run this, or ask for @drift read:.
Read docs/GRAPH_DRIFT.md. Prefer the host script. Do not rewrite the script.
./scripts/drift-read.sh
The user is the human who runs this vault on this machine. The graph is the knowledge in this vault. Do not call the graph “the Vault.”
Schedule and voice
On demand. Print the five buckets even when they are empty. Empty arrays (and drift-read: quiet on stderr) mean a clean or first-day vault.
This pass reports. It does not delete, unlink, or rewrite. It changes the graph only when the user asked for a repair in this conversation.
User config
- MCP: http://127.0.0.1:8787/mcp
FOUNDATION_API_KEYfrom the environment, else the verify key file, else the clone.env
Checks (report only)
The script pages inspect_ontology, search by type, and get. It never calls a write tool.
- Missing needed — a field marked needed is absent, null, or empty.
- Zero-edge — a live record with no live incident edges.
- Dangling refs — a declared ref field whose value is not a live record. Extra keys that happen to hold a UUID do not count.
- Retired keys — leftover identity bags still on
data(they migrate into url or repo on the next write). - Duplicate titles — live records that share a title, case-insensitive.
A first-day vault (seed types, zero user records) is quiet.
After the report
List what you found with enough ids and titles for the user to decide. Smallest next look. Not a silent rewrite. If they ask to repair in this conversation, then you may mutate; destructive tools need a key with destructive scope.
When a step finishes, name who has the work now, or say done. Cite .agents/skills/handoff/.
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.
- 2d ago First seen · 46 lines · 0 tokens per session scan A dc33d7322526
drift-read is a skill published in the GitHub repository dgraziosi/foundation (1 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 494 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 2026-09-04.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.