Borrowing it
Nothing to install: this file belongs to design-and-deliver/claude-code-autoconfig. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/design-and-deliver/claude-code-autoconfig/main/.claude/commands/autoconfig-update.mdgit clone --depth 1 https://github.com/design-and-deliver/claude-code-autoconfigWrote 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/commands/design-and-deliver/claude-code-autoconfig/autoconfig-update)<a href="https://agentmods.dev/commands/design-and-deliver/claude-code-autoconfig/autoconfig-update"><img src="https://agentmods.dev/badge/commands/design-and-deliver/claude-code-autoconfig/autoconfig-update.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.02722 |
| Opus 5 | $0.00000 | $0.01361 |
| Sonnet 5 | $0.00000 | $0.00544 |
| Haiku 4.5 | $0.00000 | $0.00272 |
Grade D, and why
autoconfig-update scanned grade D with 2 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 7d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- @sideeffect Pulls latest update files from npm, executes update instructions, tracks applied updates --> Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Auto permission mode is a **user-level** opt-in — Claude Code ignores `permissions.defaultMode: "auto"` in project `.claude/settings.json` (a repository cannot grant itself auto mode), so it only works from `~/.claude/se How it starts
The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autoconfig Update
Check for and install pending updates to your Claude Code configuration.
Style guideline: Work silently through Steps 0-3. Do not narrate internal steps, implementation details, or progress messages (e.g., "Let me check...", "The @applied block is empty..."). The first output the user sees should be the What's New list from Step 0 and/or the formatted summary in Step 4 (or the "up to date" message).
Step 0: What's New (installer handoff)
Read .claude/.autoconfig-whats-new.json. If it doesn't exist, skip silently to Step 1.
If it exists, it was written by the installer during a version upgrade and holds { from, to, segments }, where each segment is { kind, text }. Render it as the what's-new list, mapping kinds to lines:
| kind | render as |
|---|---|
heading |
⬆️ {text} (the text is self-contained, e.g. "What's new since your last update (v1.0.186):") |
group |
blank line, then **{text}:** |
item |
✅ {text} |
more |
…{text} |
latest |
✅ {text} |
Then delete .claude/.autoconfig-whats-new.json (it's one-shot — a later run must not repeat the list), and continue to Step 0b.
Step 0b: Status Beeps Opt-in (asked once)
The status beeps are opt-in, and upgraded projects have never been asked. Offer them once:
- Skip silently if any of these hold:
.claude/sounds/status-beeps.enabledor.claude/sounds/arcade-beeps.enabledexists (already on), or.claude/cca.config.jsonhas"statusBeepsPrompted": true(already asked), or- the run is headless / the question can't be answered.
- Otherwise ask with the AskUserQuestion tool:
- Question: "Turn on Waiting/Done status beeps for Claude Code?"
- Options: "Yes, enable beeps" / "No thanks"
- On yes: create the flag by writing an empty file with the Write tool:
.claude/sounds/status-beeps.enabled - On yes or no (not on skip): merge
"statusBeepsPrompted": trueinto.claude/cca.config.jsonwith the Write tool, preserving any existing keys — this is what prevents re-asking on every future update.
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.
- 7d ago First seen · 228 lines · 0 tokens per session scan D b7393a71b4d7
autoconfig-update is a command published in the GitHub repository design-and-deliver/claude-code-autoconfig (2 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,722 tokens. A static security scan graded it D with 2 findings (hidden instructions, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.