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/update-contextnpx skills add adeotek/claude-code --skill update-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 | $0.00082 | $0.00701 |
| Opus 5 | $0.00041 | $0.00351 |
| Sonnet 5 | $0.00016 | $0.00140 |
| Haiku 4.5 | $0.00008 | $0.00070 |
Grade A, and why
update-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.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Context
Refresh an existing checkpoint in .memory/<name>.md by merging preserved content with a new summary from the current session. Current State and Next Steps are always replaced; Goal, Decisions Made, and Notes are preserved and extended.
Steps
-
Extract the filename from the user's prompt. Use 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 update:
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), tell the user and suggest creating it withsave-contextfirst. -
Read
.memory/<name>.mdusing the Read tool. -
Gather fresh git state by running:
git branch --show-current 2>/dev/null git log --oneline -3 2>/dev/nullIf either fails (not a git repo), omit the git line.
-
Generate the merged update using the section-by-section rules below.
-
Write the updated content back to
.memory/<name>.md. No overwrite prompt is needed — updating is the explicit intent. -
Confirm with a brief summary of what changed, e.g., "Updated
.memory/auth-work.md— Current State and Next Steps refreshed, 2 new decisions added."
Merge Rules
Saved date and git metadata: Always replace with today's date and fresh git state.
Goal: Preserve the original paragraph. If the current session has clearly pivoted to a different objective, update the paragraph and append a parenthetical note, e.g., (updated YYYY-MM-DD: now focused on Y instead of X).
Current State: Always replace entirely — old state is stale by definition.
Key Files: Merge old and new. Keep entries still relevant to the work; add files created or meaningfully modified in this session; remove entries for files no longer relevant.
Decisions Made: Keep all existing decisions (historical context matters). Append any new non-obvious decisions from this session.
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 · 56 lines · 82 tokens per session scan A bd4e3a3a1001
update-context is a skill published in the GitHub repository adeotek/claude-code (2 stars, last pushed 4mo ago), licensed MIT. It adds 82 tokens to every session and 701 once invoked, about $0.0004 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…