Borrowing it
Nothing to install: this file belongs to lbruton/claude-context. 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/lbruton/claude-context/master/.agents/skills/context-drift/SKILL.mdgit clone --depth 1 https://github.com/lbruton/claude-contextWrote 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/lbruton/claude-context/context-drift)<a href="https://agentmods.dev/skills/lbruton/claude-context/context-drift"><img src="https://agentmods.dev/badge/skills/lbruton/claude-context/context-drift/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/lbruton/claude-context/context-drift"><img src="https://agentmods.dev/badge/skills/lbruton/claude-context/context-drift.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00197 | $0.02715 |
| Opus 5.5 | $0.00079 | $0.01086 |
| Sonnet 5.5 | $0.00039 | $0.00543 |
| Haiku 4.5 | $0.00020 | $0.00271 |
Grade A, and why
context-drift scanned grade A with 1 finding 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 5d 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/project.json 2>/dev/null # -> name Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Drift
Audits a project's in-repo .context/ foundation docs against source-code truth, and proposes
what should be captured but isn't. This is the maintenance counterpart to
/setup-foundation-context (which does the one-time migration). Once a project's foundation docs
live in .context/, this skill — not /vault-drift — keeps them honest.
Two jobs:
- Drift audit — every factual claim in
.context/verified against code. Source wins. - Promotion candidates — recurring patterns, gotchas, and decisions present in the code or
recent work but missing from
.context// CLAUDE.md. Surfaced as suggestions, never auto-added.
Relationship to /vault-drift
/vault-drift was retired in DEVS-78 (2026-09-28). The DocVault Foundation/ pages it audited stay in the frozen archive, and every active project keeps foundation docs in .context/. This skill is the only drift audit. A revived backburner project runs /setup-foundation-context first.
Arguments
[project]— project name. Auto-detected from.claude/project.jsonif omitted.--apply— open the fix workflow after the report. Default is report-only.--doc <name>— audit a single.context/doc.--no-promote— skip the promotion-candidate scan (drift audit only).
Phase 0: Project discovery
cat .claude/project.json 2>/dev/null # -> name
ls .context/*.md 2>/dev/null
- Repo root = current working directory.
- If no
.context/directory exists: STOP. "This project hasn't migrated foundation docs to.context/yet — run/setup-foundation-contextfirst." Do not fall back to DocVault.
Phase 1: Enumerate .context/ docs
Classify each .context/*.md:
- Baseline (5) —
infrastructure.md,architecture.md,coding-standards.md,design-philosophy.md,reusable-patterns.md. Always audited. - Extras — any other
.md(e.g.integrations.md,git-topology.md,implementation-gotchas.md). Audited too. - GLOSSARY.md — skip drift audit (owned by
/glossary); note its presence only. - Unpopulated stubs — files whose sections are still
<!-- TODO: fill from code -->. Do not flag as drift; list them under "needs fill" so the user (or this skill's promotion pass) can populate them.
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.
- 5d ago Changed e2c226209241
- 9d ago Changed c88fb486facb
- 11d ago First seen · 232 lines · 197 tokens per session scan A eeb08e47a61b
context-drift is a skill published in the GitHub repository lbruton/claude-context (2 stars, last pushed 5d ago), licensed MIT. It adds 197 tokens to every session and 2,715 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-17.
Other skills, from other repositories
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, timelines, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn), including the Learn from conversations and Learn from Memory…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…