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.
git clone --depth 1 https://github.com/indranildchandra/claude-local-starterWrote 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/indranildchandra/claude-local-starter/disable-safe-yolo)<a href="https://agentmods.dev/commands/indranildchandra/claude-local-starter/disable-safe-yolo"><img src="https://agentmods.dev/badge/commands/indranildchandra/claude-local-starter/disable-safe-yolo/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/commands/indranildchandra/claude-local-starter/disable-safe-yolo"><img src="https://agentmods.dev/badge/commands/indranildchandra/claude-local-starter/disable-safe-yolo.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 | $0.00000 | $0.00604 |
| Opus 5 | $0.00000 | $0.00302 |
| Sonnet 5 | $0.00000 | $0.00121 |
| Haiku 4.5 | $0.00000 | $0.00060 |
Grade B, and why
disable-safe-yolo 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 10d 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.
`<repo>/.claude/settings.json`. `defaultMode` is only removed if it still matches the value yolo set. How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Disable safe-yolo permissions for a repository.
Removes ONLY the allow/deny entries and defaultMode listed in ~/.claude/claude-safe-yolo-permissions.txt from
<repo>/.claude/settings.json. defaultMode is only removed if it still matches the value yolo set.
Idempotent — manually added permissions are never touched.
If the file becomes empty after removal, it is deleted entirely.
Feel free to edit ~/.claude/claude-safe-yolo-permissions.txt as your need evolves.
Example invocations (natural language):
/disable-safe-yolo/disable-safe-yolo in the current repo/disable-safe-yolo for your-directory/your-repo/disable-safe-yolo dry run— preview what would be removed without making changes
Step 1 — Determine target directory
Check if the user passed a path or natural language hint in the arguments:
- If a path is mentioned (e.g. "for /some/path", "in /some/path") → use that path directly, skip to Step 2.
- If the user says "dry run", "preview", or "show me" → note this for Step 2.
- Otherwise, auto-detect using this logic:
- From your environment context, collect all known working directories (primary + additional).
- Filter out non-repo paths — exclude anything under
~/.claude,~/.claude-work,/tmp, or/var. - Count what remains:
- Exactly one candidate → announce it and proceed directly to Step 2 (no confirmation yet):
"The only non-excluded working directory is ."
- Multiple candidates → list them and ask:
"Which directory should I disable safe-yolo in?" Wait for reply before continuing.
- Zero candidates → ask the user to paste the full path.
- Exactly one candidate → announce it and proceed directly to Step 2 (no confirmation yet):
Step 2 — Show dry-run summary and confirm with user
Run the dry-run to show exactly what permissions would be removed and what would be preserved:
~/.claude/disable-safe-yolo.sh --dry-run --dir="<RESOLVED_DIR>"
Then ask the user directly in the conversation:
"Safe-yolo will be disabled in <RESOLVED_DIR>. Does this directory look correct and do you want to proceed? (y/n)"
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.
- 10d ago First seen · 53 lines · 0 tokens per session scan B e9ac45edb647
disable-safe-yolo is a command published in the GitHub repository indranildchandra/claude-local-starter (13 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 604 tokens. 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 2026-08-30.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.