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/nocodework/ai-context-kit/refresh-contextnpx skills add nocodework/ai-context-kit --skill refresh-contextgit clone --depth 1 https://github.com/nocodework/ai-context-kitWhat 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 | $0.00090 | $0.00767 |
| Opus 5 | $0.00045 | $0.00383 |
| Sonnet 5 | $0.00018 | $0.00153 |
| Haiku 4.5 | $0.00009 | $0.00077 |
Grade A, and why
refresh-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 2d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
refresh-context — keep your context files current
Your job is to review a context file that already exists and bring it up to date — a maintenance pass, not a rebuild. A stale context is worse than none: it makes AI confidently wrong in your name.
Which skill to use
- No file yet → use the
personal-contextorcompany-contextskill to build one. - File exists, needs a check-up → this skill.
If the user asks to "build" and a file already exists, the build skills handle that too — this skill is for an explicit review / refresh / audit pass.
How to run it
-
Find the files. Look in the current directory for
personal-context.mdandcompany-context.md. If neither exists, say so and point to the build skills. If both exist, refresh them one at a time (ask which first). -
Read and date-check. Read the file. Find the
_Last updated: YYYY-MM_line and say how old it is in plain terms ("this was last updated 5 months ago"). Give a two-line summary of what the file currently says so the user has it in mind. -
Go section by section — probe, don't just ask "what changed?" For each section, read it back in one line and check:
- Is this still true? Roles, offers, clients and positioning drift over time.
- Is anything aspirational-but-not-real, or no longer how they actually work?
- Anything to cut — an old side project, a client you no longer serve, a goal you hit or dropped? Ask them to confirm, correct, or cut. Keep it a quick pass, not a full re-interview.
-
Check for gaps against the template. Compare the file's sections to the reference list below. If a useful section is missing, offer to add it — don't force it.
-
Rewrite and report. Apply the changes, keep the user's own words and tone, refresh the
_Last updated:_line to the current month, and keep the footer line intact. Then show a short summary of what changed, e.g. "updated: offer, clients · added: goals · removed: old side project."
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.
- 2d ago First seen · 48 lines · 90 tokens per session scan A e9d65a968885
refresh-context is a skill published in the GitHub repository nocodework/ai-context-kit (24 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 767 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 2026-08-30.
Other skills, from other repositories
repomix
Pack and analyze codebases into AI-friendly single files using Repomix. Use when the user wants to explore repositories, analyze code structure, find patterns, check token counts, or prepare codebase context for AI analysis. Supports both local directories and remote GitHub repositories.
seo-audit
Audit and fix a website's technical SEO and AI-search (GEO) readiness against Google's official guidance, page by page, ending in a computed SEO/GEO score. Use when asked to audit SEO, fix indexing or crawling problems, check canonicals/hreflang/sitemaps/structured data, diagnose why pages are not indexed or traffic…
prompt-architect
Analyzes and improves prompts using 31 frameworks across 7 intent categories. Use when a user wants to improve, rewrite, structure, or engineer a prompt — including requests like "help me write a better prompt", "improve this prompt", "what framework should I use", "make this prompt more effective", or any prompt…
tidy
A simple example skill for cleaning up a project.
extreme-router-gateway-engine
AI Gateway routing, provider management, and core engine expertise for ExtremeRouter. Use when working on request routing, provider fallback, token refresh, format translation, streaming, or when the user asks about "how does routing work", "add a new provider", "fix the fallback logic", "optimize token usage", or…
extreme-router-refactor
Code refactoring, tech debt cleanup, and code review expertise for ExtremeRouter. Use when cleaning up code, fixing bugs, reviewing PRs, identifying tech debt, or when the user asks to "improve this code", "fix this mess", "why is this broken", "make this cleaner", or mentions code smells, duplication, or poor…