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 JustinThomas2/agentrc --skill update-configgit clone --depth 1 https://github.com/JustinThomas2/agentrcWrote 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/justinthomas2/agentrc/update-config)<a href="https://agentmods.dev/skills/justinthomas2/agentrc/update-config"><img src="https://agentmods.dev/badge/skills/justinthomas2/agentrc/update-config/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/justinthomas2/agentrc/update-config"><img src="https://agentmods.dev/badge/skills/justinthomas2/agentrc/update-config.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 | $0.00067 | $0.00599 |
| Opus 5.5 | $0.00027 | $0.00240 |
| Sonnet 5.5 | $0.00013 | $0.00120 |
| Haiku 4.5 | $0.00007 | $0.00060 |
Grade B, and why
update-config scanned grade B with 1 finding 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 2mo 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
like `~/.claude/settings.json` is a symlink into `~/agentrc/claude/`, What it actually says
CHANGE = $ARGUMENTS - if that reads as a literal placeholder instead of a description, use the description I gave when invoking this skill. If I gave none, ask what config change I want before doing anything else.
Agent config on this machine is managed by the agentrc repo. What looks
like ~/.claude/settings.json is a symlink into ~/agentrc/claude/,
and the same goes for the other agent config files. Two consequences:
- File-editing tools refuse to write through symlinks. Always resolve
the real path first with
readlink -f <file>and edit that (e.g.~/agentrc/claude/settings.json). - A config edit is a repo change. It goes through the git workflow in AGENTS.md, never a silent in-place edit.
Your task
- Resolve the target. Run
readlink -fon the config file to get its repo path. If the file is NOT a symlink into~/agentrc, stop and ask whether it should be added to the repo first. - Branch per AGENTS.md: switch to main (stash or commit unrelated WIP, never carry it along), pull, then branch off the fresh main.
- Make the edit in the repo file. Read the file first and merge with what is there; never regenerate the whole file.
- Permission rules must use forms the permission checker actually
matches. File rules use
Edit(path)- theEdit(...)form covers all file-editing tools (Edit, Write, NotebookEdit). Never writeWrite(path)rules; they are silently ignored and cause startup warnings. - Validate JSON files with
jq . <file>; ifjqis missing on the machine, fall back topython3 -m json.tool <file>. For settings semantics (hook events, schema fields), defer to the harness's own bundled config documentation rather than guessing. - Commit with a Conventional Commit message, then STOP. Show me the
diff and wait - per AGENTS.md, never push or open a PR without my
explicit go-ahead. New skill folders also need
scripts/fetch-skills.shre-run to link them; mention it when that applies.
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.
- 2mo ago First seen · 45 lines · 67 tokens per session scan B 48cd44e0ea12
update-config is a skill published in the GitHub repository JustinThomas2/agentrc (2 stars, last pushed 3mo ago), licensed MIT. It adds 67 tokens to every session and 599 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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…
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…
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…