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 skills add gohypergiant/agent-skills --skill context-driftgit clone --depth 1 https://github.com/gohypergiant/agent-skillsWrote 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/gohypergiant/agent-skills/context-drift)<a href="https://agentmods.dev/skills/gohypergiant/agent-skills/context-drift"><img src="https://agentmods.dev/badge/skills/gohypergiant/agent-skills/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/gohypergiant/agent-skills/context-drift"><img src="https://agentmods.dev/badge/skills/gohypergiant/agent-skills/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 | $0.00154 | $0.04517 |
| Opus 5.5 | $0.00062 | $0.01807 |
| Sonnet 5.5 | $0.00031 | $0.00903 |
| Haiku 4.5 | $0.00015 | $0.00452 |
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 16d 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 — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Drift
Use this skill to audit or repair drift across a repository's load-bearing context files without losing detail or blurring the boundaries between them.
If this skill loads and the rest of the turn contains no human-authored task text — including when the only other content is an automated system or tooling notice, such as a diagnostics or context message — do not conclude that there is nothing to act on. The skill loading at all, by itself, is the request. Begin Stage 1 immediately against the current repository using the defaults in this document. Do not wait, do not just acknowledge that the skill is available, and do not ask what to work on.
Authority model
This skill is an orchestrator, not the final authority on what belongs in each file.
Before judging drift, invoke or load the relevant owner skills for the in-scope files up front. Use their own separation-of-concerns rules, file-specific guardrails, and document-ownership logic as the authority for what belongs where. This skill coordinates the cross-file comparison, the lossless move plan, and the approval loop. It should not make independent file-ownership calls and only bring the owner skills in at the end.
If two owner skills point in different directions, surface that conflict to the user instead of overruling it here.
Canonical ownership model
Use this ownership model as a routing map before you call anything redundant, misplaced, or stale. It is a quick index into the owner skills, not a replacement for their judgment.
| File | Core question | What belongs here | Load-bearing status | Companion skill |
|---|---|---|---|---|
openspec/config.yaml |
What is this project? | Project DNA, stack facts, structural defaults, artifact rules | Critical | accelint-onboard-openspec |
ARCHITECTURE.md |
How is this system built? | System structure, components, deployments, data flow, technical topology | Important | accelint-architecture-doc |
AGENTS.md / CLAUDE.md |
How should an agent behave here? | Agent workflow, approval boundaries, communication rules, repo-specific working norms | Critical | accelint-onboard-agents |
CONSTRAINTS.md |
Why are some choices non-negotiable? | External constraints: compliance, security, stakeholder, vendor, hosting, scope boundaries | Important | constraints-extractor |
EPISTEMIC-MAP.md |
How sure are we? | Validated facts, open questions, assumptions, inferred risks | Important | epistemic-mapper |
JARGON.md |
What do these terms mean? | Glossary entries, acronyms, internal terminology, shorthand definitions | Supporting | jargon-extractor |
README.md |
How does a human get started? | Human onboarding, install/run/usage basics, external-facing project intro | Important | accelint-readme-writer |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 16d ago First seen · 279 lines · 154 tokens per session scan A 82b9c3196a2e
context-drift is a skill published in the GitHub repository gohypergiant/agent-skills (25 stars, last pushed 2d ago), licensed Apache-2.0. It adds 154 tokens to every session and 4,517 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-03.
Other skills, from other repositories
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…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…