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/jkheadley/instar/secret-setupnpx skills add JKHeadley/instar --skill secret-setupgit clone --depth 1 https://github.com/JKHeadley/instarWrote 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/jkheadley/instar/secret-setup)<a href="https://agentmods.dev/skills/jkheadley/instar/secret-setup"><img src="https://agentmods.dev/badge/skills/jkheadley/instar/secret-setup.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 | $0.00035 | $0.02235 |
| Opus 5 | $0.00017 | $0.01118 |
| Sonnet 5 | $0.00007 | $0.00447 |
| Haiku 4.5 | $0.00003 | $0.00224 |
Grade B, and why
secret-setup scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Subtle steeringlowPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
Do NOT assume the user has any specific credentials in Bitwarden. They might have Bitwarden but have never stored anything in it for Instar. Only check what's actually there — never tell the user "I need to restore your Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 600 "$HOME/.instar/secrets/.bw-session" How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Secret Management Setup
You are guiding a user through choosing and configuring how their Instar agent stores secrets (API tokens, bot credentials, etc). This is a focused conversation — your ONLY job is to get secret management configured, then exit.
CRITICAL RULES
1. No Interactive CLI Commands — WILL HANG FOREVER
Claude Code's Bash tool CANNOT handle stdin prompts. Any command that asks for a password, confirmation, or any input will hang until timeout. There is NO workaround — you cannot type into a running command.
UNDERSTAND THIS ABOUT --raw: The --raw flag ONLY changes the output format. It does NOT prevent interactive prompts. bw unlock --raw STILL prompts for a password and WILL HANG. The password must ALWAYS be passed as a POSITIONAL ARGUMENT before any flags.
Commands that WILL HANG (never run these):
bw unlock --raw # HANGS — no password argument
bw unlock # HANGS — prompts for password
bw login --raw # HANGS — no email/password
bw login # HANGS — prompts for credentials
echo "text" && bw unlock --raw # HANGS — bw still prompts
read -s VARIABLE # HANGS — waits for hidden input
Commands that WORK (use ONLY these patterns):
bw unlock "ACTUAL_PASSWORD_HERE" --raw # Returns session key immediately
bw login "EMAIL" "PASSWORD" --raw # Returns session key immediately
bw status --raw # Returns JSON, never prompts
which bw 2>/dev/null # Checks if installed, never prompts
bw --version # Returns version, never prompts
THE RULE: You MUST have the user's password as text BEFORE running any unlock/login command. Ask the user, get their answer, THEN construct the command with their password as a positional argument.
2. NEVER Use AskUserQuestion for Passwords, Emails, or Free-Text
This is the #1 UX failure mode. AskUserQuestion is ONLY for multiple-choice DECISIONS (pick A or B or C). It must NEVER be used to collect passwords, email addresses, tokens, or any free-text input.
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.
- 6d ago First seen · 211 lines · 35 tokens per session scan B 0f4365713d96
secret-setup is a skill published in the GitHub repository JKHeadley/instar (77 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 2,235 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (subtle steering, asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
typescript-expert
TypeScript and JavaScript expert with deep knowledge of type-level programming, performance optimization, monorepo management, migration strategies, and modern tooling.
regenerate-grpc-stubs
Regenerate Python + TypeScript gRPC stubs after editing proto files. Use when proto/.proto changes, imports from bindu.grpc.generated fail, CI reports generated-code drift, or HandleMessages calls fail with proto mismatch.
V3 CLI Modernization
CLI modernization and hooks system enhancement for claude-flow v3. Implements interactive prompts, command decomposition, enhanced hooks integration, and intelligent workflow automation.
V3 DDD Architecture
Domain-Driven Design architecture for claude-flow v3. Implements modular, bounded context architecture with clean separation of concerns and microkernel pattern.
javascript-sast
JavaScript and Node.js security scanning. Checks dependency vulnerabilities via npm audit and source patterns for XSS, eval, and prototype pollution.
sdk
Guide users building apps, scripts, CI pipelines, or automations on top of the Cursor TypeScript SDK (@cursor/sdk). Use when the user mentions integrating, installing, or writing code against the Cursor SDK; says Agent.create, Agent.prompt, Agent.resume, agent.send, run.stream, CursorAgentError, or @cursor/sdk; asks…