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 agents/pdumicz/secret-shuttle/codex-instructions.examplegit clone --depth 1 https://github.com/pdumicz/secret-shuttleWhat 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 | $0.00000 | $0.00484 |
| Opus 5 | $0.00000 | $0.00242 |
| Sonnet 5 | $0.00000 | $0.00097 |
| Haiku 4.5 | $0.00000 | $0.00048 |
Grade A, and why
codex-instructions.example scanned grade A with 0 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 2d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Codex Instructions For Secret Shuttle
When handling secrets, route the secret moment through Secret Shuttle.
Setup before the first secret operation:
npx secret-shuttle init
Do:
- navigate with the browser normally until a secret becomes visible or a secret value field is focused
- stop observing before the secret is visible to the model
- run Secret Shuttle commands from the terminal
- report only refs, fingerprints, and status
- approve production actions in the Secret Shuttle window your browser opens
Do not:
- ask the user to paste secret values
- read DOM or accessibility text while blind mode is active
- take screenshots while blind mode is active
- inspect console, network bodies, or clipboard while blind mode is active
- print raw values from
.env, CLI output, or browser fields
Use:
# Provision a new local secret straight into a destination (one approval):
secret-shuttle provision --secret INTERNAL_CRON_SECRET \
--from random_32_bytes \
--environment production \
--to vercel:production
# Capture a secret revealed on a page — mark the controls, then reveal-capture
# (blind mode is daemon-managed inside the transaction; you never see the value):
secret-shuttle browser mark pick --as reveal-btn
secret-shuttle browser mark focused --as revealed-field
secret-shuttle reveal-capture --name STRIPE_WEBHOOK_SECRET --env production \
--source stripe --reveal-handle reveal-btn --field-handle revealed-field \
--allow-domain dashboard.stripe.com
# Write a secret into a focused field and submit, verifying a success marker:
secret-shuttle browser mark focused --as value-field
secret-shuttle browser mark pick --as save-button
secret-shuttle inject-submit --ref ss://stripe/prod/STRIPE_WEBHOOK_SECRET \
--field-handle value-field --submit-handle save-button --success-text "Saved"
To hand a secret to an external binary, use a template:
secret-shuttle template run vercel-env-add \
--ref ss://stripe/prod/STRIPE_WEBHOOK_SECRET \
--param name=STRIPE_WEBHOOK_SECRET \
--param environment=production
Production actions require the human to approve in the Secret Shuttle window their browser opens. There is no CLI flag that bypasses approval.
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.
- 2d ago First seen · 61 lines · 0 tokens per session scan A 0228846f9207
codex-instructions.example is an agent published in the GitHub repository pdumicz/secret-shuttle (4 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 484 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.