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 commands/marcusquinn/aidevops/vaultgit clone --depth 1 https://github.com/marcusquinn/aidevopsWrote 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/marcusquinn/aidevops/vault)<a href="https://agentmods.dev/commands/marcusquinn/aidevops/vault"><img src="https://agentmods.dev/badge/commands/marcusquinn/aidevops/vault.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 | $0.00021 | $0.00738 |
| Opus 5 | $0.00010 | $0.00369 |
| Sonnet 5 | $0.00004 | $0.00148 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade A, and why
vault 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use this command guide for aidevops vault and Vault-related aidevops fleet
flows. Arguments: $ARGUMENTS
Safety contract
- Never paste Vault passphrases, recovery material, private keys, or raw secrets into AI chat, CLI arguments, environment variables, logs, issue comments, PR bodies, screenshots, or fixtures.
- Run commands that need unlock material in a local terminal with the helper's hidden prompt.
- Treat Git, object storage, secure messaging, SSH, Tailscale/VPN, and VPS disks as untrusted transports. Sync only encrypted payloads plus signed metadata.
- Status, setup-state, public fingerprints, and sanitized error codes are safe evidence; secret values are not.
Local Vault commands
aidevops vault init
aidevops vault setup-state
aidevops vault status
aidevops vault unlock
aidevops vault lock
aidevops vault lost-passphrase
aidevops vault lost-passphrase archive-and-start-fresh
Expected behaviour:
initasks locally for a 12+ character passphrase, confirmation, and the exact no-recovery acknowledgement. Store the passphrase in a trusted password manager with backups.unlockuses a local hidden prompt; never pass unlock material as an argument or environment variable.setup-stategates migration. Real protected-data migration remains blocked until a fresh unlock proves the harmless setup test record is readable.lost-passphrase archive-and-start-fresharchives ciphertext and metadata; it does not decrypt or delete the archive.
Fleet and sync flows
Use workflows/vault-fleet.md before advising multi-device operations.
- Device onboarding: exchange public fingerprints, verify through an authenticated human/local channel, then sign trust updates from an existing trusted device.
- Sync: export/import encrypted collection records only; plaintext filenames, private paths, client names, subjects, and collection entry IDs must not appear in transport-visible names.
- Remote lock: safe protective action when signed by a trusted device.
- Unlock-request: preferred remote access pattern; approval happens locally and rewraps only scoped collection keys.
- True remote unlock: default-disabled unless an audited, opt-in, device-bound, short-lived policy exception exists; passphrases still never travel through chat, args, env vars, logs, or fixtures.
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.
- yesterday First seen · 82 lines · 21 tokens per session scan A a2b9bdcb3bdf
vault is a command published in the GitHub repository marcusquinn/aidevops (392 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 738 once invoked, about $0.0001 per session on Opus 5. 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 2026-09-03.
Other commands, from other repositories
gsd:new-project
Initialize a new project with deep context gathering and PROJECT.md.
gsd:new-milestone
Start a new milestone cycle — update PROJECT.md and route to requirements.
gsd:help
Show available GSD commands and usage guide.
gsd:plan-phase
Create detailed execution plan for a phase (PLAN.md) with verification loop.
gsd:execute-phase
Execute all plans in a phase with wave-based parallelization.
gsd:audit-milestone
Audit milestone completion against original intent before archiving.