A report-only check for drift in a knowledge graph, such as missing fields, isolated records, broken references, leftover identity keys, or duplicate titles. It reads the graph and reports findings without repairing them.

It helps inspect graph structure, find incomplete records, detect references to missing records, identify disconnected items, and report duplicate titles.

It helps reveal inconsistencies without accidentally changing or deleting graph data, so a person can review problems before requesting repairs.

How dgraziosi/foundation configures Claude Code and Codex

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/drift-read/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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dgraziosi/foundation/drift-read/github.svg)](https://agentmods.dev/skills/dgraziosi/foundation/drift-read)

Your own site

<a href="https://agentmods.dev/skills/dgraziosi/foundation/drift-read"><img src="https://agentmods.dev/badge/skills/dgraziosi/foundation/drift-read/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dgraziosi/foundation/drift-read"><img src="https://agentmods.dev/badge/skills/dgraziosi/foundation/drift-read.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 494 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00494
Opus 5.5	$0.00000	$0.00198
Sonnet 5.5	$0.00000	$0.00099
Haiku 4.5	$0.00000	$0.00049

Measured 2mo ago against content hash dc33d7322526, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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/drift-read/SKILL.md · 46 lines

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_KEY from 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/.

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.

2mo ago First seen · 46 lines · 0 tokens per session scan A dc33d7322526

Subscribe to this mod's changes

drift-read is a skill published in the GitHub repository dgraziosi/foundation (1 stars, last pushed today), 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.

Analytics and metrics Debugging

drift-read next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
drift-readdgraziosi/foundation	Skill	1	today	MIT	A	0	Claude Code, Codex
systematic-debuggingopen-metadata/OpenMetadata	Skill	16k	yesterday	Apache-2.0	A	37	Claude Code
log-error-digestzebbern/claude-code-guide	Skill	4.7k	3d ago	MIT	A	71	Claude Code, Codex
cwv-optimizeradobe/skills	Skill	319	yesterday	Apache-2.0	A	112	Claude Code
ci-fixersipyourdrink-ltd/bernstein	Skill	1.2k	yesterday	Apache-2.0	A	15	Claude Code, Codex
incident-response-incident-responsermyndharis/antigravity-skills	Skill	1.9k	23d ago	MIT	A	36	Claude Code
triaging-web-analytics-supportPostHog/posthog	Skill	41k	today	none	A	151	Claude Code, Codex

foundation: Skill for Claude Code