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/yonatangross/orchestkitWrote 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/rules/yonatangross/orchestkit/cc-bare-auth-gotcha)<a href="https://agentmods.dev/rules/yonatangross/orchestkit/cc-bare-auth-gotcha"><img src="https://agentmods.dev/badge/rules/yonatangross/orchestkit/cc-bare-auth-gotcha/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/rules/yonatangross/orchestkit/cc-bare-auth-gotcha"><img src="https://agentmods.dev/badge/rules/yonatangross/orchestkit/cc-bare-auth-gotcha.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 | $0.00028 | $0.01750 |
| Opus 5 | $0.00014 | $0.00875 |
| Sonnet 5 | $0.00006 | $0.00350 |
| Haiku 4.5 | $0.00003 | $0.00175 |
Grade C, and why
cc-bare-auth-gotcha scanned grade C 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 3d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 600 ~/.claude/.api-key Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
> ~/.claude/settings.json How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rule: claude --bare auth is broken — never use it in CI
Status: confirmed CC 2.1.81–2.1.143 · upstream bug filed anthropics/claude-code#60155 · prior incident orchestkit#1629
The trap
The --bare flag's --help text promises:
Anthropic auth is strictly ANTHROPIC_API_KEY or apiKeyHelper via --settings (OAuth and keychain are never read).
All three documented paths fail. Every invocation in --bare mode returns:
{"is_error":true, "result":"Not logged in · Please run /login"}
regardless of whether the API key is supplied via env var, --settings.apiKey, or --settings.apiKeyHelper.
Don't do this
# WRONG — will silently fail every claude invocation
- env:
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
run: |
claude -p --bare --max-turns 4 --output-format json "..."
Do this
# RIGHT — FILE-BACKED apiKeyHelper + plain `claude -p`
#
# Critical: the helper script does NOT inherit $ANTHROPIC_API_KEY from
# the parent step's env. CC strips env before spawning the helper.
# Verified locally 2026-05-18 (CC 2.1.143): "apiKeyHelper failed: did
# not return a value". The helper must read from a file the workflow
# writes.
- name: Configure Claude apiKeyHelper
env:
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
run: |
mkdir -p ~/.claude
umask 077
printf '%s' "$ANTHROPIC_API_KEY" > ~/.claude/.api-key
chmod 600 ~/.claude/.api-key
printf '#!/bin/sh\ncat %s/.claude/.api-key\n' "$HOME" \
> ~/.claude/api-key-helper.sh
chmod +x ~/.claude/api-key-helper.sh
printf '{"apiKeyHelper":"%s/.claude/api-key-helper.sh"}\n' "$HOME" \
> ~/.claude/settings.json
- name: Analyze
run: |
claude -p --max-turns 4 --output-format json --no-session-persistence "..."
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.
- 3d ago First seen · 157 lines · 28 tokens per session scan C fdf0734720a7
cc-bare-auth-gotcha is a cursor rule published in the GitHub repository yonatangross/orchestkit (264 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 1,750 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (asks for root, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-09.
Other cursor rules, from other repositories
pn-tool-risk-policy
MCP tool risk tiers, HITL gates, and when to use approvalcheckpoint and gatelogappend. Use for safety reviews and workflow audits.
sciclaw-papercuts
Papercuts from Sol/ImageMagick/release cycles — release, brew, CI, and workspace hygiene for sciClaw agents.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.