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 agentmods add skills/adeotek/claude-code/load-contextnpx skills add adeotek/claude-code --skill load-contextgit clone --depth 1 https://github.com/adeotek/claude-codeWhat 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 | $0.00106 | $0.00498 |
| Opus 5 | $0.00053 | $0.00249 |
| Sonnet 5 | $0.00021 | $0.00100 |
| Haiku 4.5 | $0.00011 | $0.00050 |
Grade A, and why
load-context 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 yesterday.
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
Load Context
Load a previously saved context from .memory/<name>.md in the current working directory and actively re-establish it in the conversation.
Steps
-
Extract the name from the user's prompt using the same kebab-case normalization as save-context (e.g., "auth work" →
auth-work). -
If no name was given, list available contexts and ask the user which to load:
ls .memory/*.md 2>/dev/nullPresent the names without the
.mdextension and without the.memory/path prefix. -
If the file doesn't exist (
.memory/<name>.mdnot found), list available contexts and suggest the closest match by name similarity. Do not fail silently. -
Read
.memory/<name>.mdusing the Read tool. -
Present the loaded context in two parts:
- Display the full file content so the user can scan it
- Follow with a brief conversational restatement of the current state and next steps, so the context is immediately active without requiring the user to re-read the file
Presentation Pattern
After displaying the file, restate the key points in 2–3 sentences:
Loaded auth-work (saved 2026-04-21). We were implementing JWT authentication middleware — the core logic in
middleware.tsis done and tests pass. The remaining work is creating the PR and adding an integration test.
Tailor this summary to what's most immediately actionable — prioritize Current State and Next Steps from the file. If the file has a Notes section with blockers or caveats, mention those too.
This positions the conversation to continue naturally. The user should be able to say "ok, let's do the next step" without needing to explain anything further.
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.
- yesterday First seen · 37 lines · 106 tokens per session scan A 531be23e2f85
load-context is a skill published in the GitHub repository adeotek/claude-code (2 stars, last pushed 4mo ago), licensed MIT. It adds 106 tokens to every session and 498 once invoked, about $0.0005 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…