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/opencoven/coven/1passwordnpx skills add OpenCoven/coven --skill 1passwordgit clone --depth 1 https://github.com/OpenCoven/covenWrote 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/opencoven/coven/1password)<a href="https://agentmods.dev/skills/opencoven/coven/1password"><img src="https://agentmods.dev/badge/skills/opencoven/coven/1password.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 | $0.00050 | $0.00991 |
| Opus 5 | $0.00025 | $0.00495 |
| Sonnet 5 | $0.00010 | $0.00198 |
| Haiku 4.5 | $0.00005 | $0.00099 |
Grade A, and why
1password scanned grade A 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Provides whitelisted access for other skills (ask-curl, GitHub, etc.) How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1Password Secret Management
Securely store and retrieve secrets. Never expose them in chat, logs, or files.
Prerequisites
opCLI installed:brew install --cask 1password-cli- Signed in:
op signin(or service account viaOP_SERVICE_ACCOUNT_TOKEN) - For biometric unlock: enable in 1Password desktop app → Settings → Developer → CLI integration
Core Commands
Read a secret
op read "op://VaultName/ItemName/FieldName"
List vaults
op vault list --format json | jq '.[].name'
List items in a vault
op item list --vault "Development" --format json | jq '.[].title'
Create an item
op item create \
--category login \
--vault "Development" \
--title "Service API Key" \
--field "credential=secret_value_here"
Search items
op item list --format json | jq '.[] | select(.title | test("github"; "i"))'
Environment Files (Secret References)
Create env files with op:// references — secrets are resolved at runtime, never stored on disk.
Setup for ask-curl
mkdir -p ~/.config/ask-curl
# Create env file with secret references (NOT actual secrets)
cat > ~/.config/ask-curl/env.curl << 'ENV'
GITHUB_TOKEN=op://Development/GitHub PAT/credential
OPENAI_API_KEY=op://Development/OpenAI/api key
SLACK_WEBHOOK=op://Development/Slack Webhook/url
ENV
Use with op run
# Inject secrets from env file into a command
op run --env-file=~/.config/ask-curl/env.curl -- curl -s \
-H "Authorization: Bearer $GITHUB_TOKEN" \
"https://api.github.com/user"
# Inject secrets into any command
op run --env-file=~/.config/ask-curl/env.curl -- node script.js
Skill Whitelisting
Control which skills can access which secrets by using separate env files per skill:
~/.config/ask-curl/env.curl # HTTP/API secrets for ask-curl
~/.config/github/env.gh # GitHub-specific secrets
~/.config/openclaw/env.gateway # Gateway/infra secrets
Each env file contains only the op:// references that skill needs — principle of least privilege.
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.
- 5d ago First seen · 141 lines · 50 tokens per session scan A e6e680014b7e
1password is a skill published in the GitHub repository OpenCoven/coven (46 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 991 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
1password
Read, write and inject secrets with the 1Password CLI (op). Look up logins/API keys/SSH keys, resolve op:// secret references, run a command with secrets as env vars (op run), fill config templates (op inject), and create/edit items. Triggers on /1password, "get my API key", "what's the password for X", "put this…
agentsecrets
Zero-knowledge secrets infrastructure — AI agents manage the complete credential lifecycle without ever seeing values.
agentsecrets
Zero-knowledge secrets infrastructure — AI agents manage the complete credential lifecycle without ever seeing values.
cis-aws-compute-3.6
Ensure secrets are not passed as container environment variables in Amazon ECS task definitions.
provisioning-wizard
Bash wizard for human-only setup.
Secrets Management
Secrets manager usage, rotation, and least privilege — so credentials are injected at deploy time, rotated on a schedule, and never end up in artifacts, config, or logs.