context-drift

context-drift is a skill for Claude Code, Codex from suuus/ape-context. It costs 18 tokens per session (998 once invoked), scanned A, original, MIT.

A project checker that compares the tools and services found in your codebase with your MCP configuration and agent instructions.

In plain words
What is it for?
Use it to review project changes, check MCP server connections, find stale references in copilot-instructions.md, and identify available updates.
Why use it?
It helps catch configuration drift: newly added tools without an MCP server, removed tools still listed, unavailable servers, outdated instructions, and newer server package versions.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/suuus/ape-context/context-drift
Any agent
npx skills add suuus/ape-context --skill context-drift
Clone the repo
git clone --depth 1 https://github.com/suuus/ape-context

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 context-drift

README.md
[![agentmods](https://agentmods.dev/badge/skills/suuus/ape-context/context-drift.svg)](https://agentmods.dev/skills/suuus/ape-context/context-drift)
Your own site
<a href="https://agentmods.dev/skills/suuus/ape-context/context-drift"><img src="https://agentmods.dev/badge/skills/suuus/ape-context/context-drift.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 998 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00018 $0.00998
Opus 5 $0.00009 $0.00499
Sonnet 5 $0.00004 $0.00200
Haiku 4.5 $0.00002 $0.00100

Measured 3d ago against content hash 36666f315489, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-drift 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.

.github/skills/context-drift/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Re-scan the project and compare against the current .mcp.json and copilot-instructions.md to detect configuration drift.

What to check

1. Stack drift

Run the same detection as Phase 1 (Detect):

  • Scan package files, CI/CD, infrastructure, cloud indicators
  • Compare detected tools against what's configured in .mcp.json
  • Flag new tools not covered by any MCP server: "You added Terraform since last setup — want to add an MCP server for it?"
  • Flag removed tools still configured: "The Datadog config is still in .mcp.json but no Datadog references were found in the project"

2. MCP server health

For each server in .mcp.json:

  • Attempt a lightweight read-only tool call
  • Report: ✅ connected / ⚠️ auth expired / ❌ unreachable

3. Instruction staleness

  • Compare the tools referenced in copilot-instructions.md against .mcp.json
  • Flag instructions that reference servers no longer configured
  • Flag configured servers not mentioned in instructions

4. Dependency updates

  • Check if any configured MCP server packages have newer versions available
  • Report: "atlassian-mcp-server: using @latest (current), github-mcp-server: using @latest (current)"

5. Intent impact

Assess whether detected changes affect the team's distilled intent, constraints, or autonomy boundaries:

  • Security tools added or removed (e.g., new scanning tool, removed WAF)
  • Deployment pipeline changed (e.g., new CI/CD system, changed deploy targets)
  • Cloud platform changed (e.g., new provider, new services adopted)
  • Monitoring/observability changed (e.g., switched from Datadog to App Insights)
  • Access control changed (e.g., new auth provider, changed RBAC model)

If any intent-relevant changes are detected, classify them as 🔴 action-required.

Severity classification

Classify each drift item by severity:

Level Icon Meaning Examples
Info ℹ️ Minor, no action needed Package version update available
Warning ⚠️ Should be addressed soon New tool detected, auth expiring, stale instruction reference
Action required 🔴 Needs immediate attention Auth failed, tool removed but still configured, intent-affecting stack changes

Read the full file on GitHub · 102 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 First seen · 102 lines · 18 tokens per session scan A 36666f315489

Subscribe to this mod's changes

context-drift is a skill published in the GitHub repository suuus/ape-context (2 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 998 once invoked, about $0.0001 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.

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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens