Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add queelius/claude-anvil/plugin install alex-confidentialWrote 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/queelius/claude-anvil/confidential)<a href="https://agentmods.dev/skills/queelius/claude-anvil/confidential"><img src="https://agentmods.dev/badge/skills/queelius/claude-anvil/confidential/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/skills/queelius/claude-anvil/confidential"><img src="https://agentmods.dev/badge/skills/queelius/claude-anvil/confidential.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 | $0.00049 | $0.01467 |
| Opus 5 | $0.00024 | $0.00733 |
| Sonnet 5 | $0.00010 | $0.00293 |
| Haiku 4.5 | $0.00005 | $0.00147 |
Grade A, and why
confidential 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Confidentiality Toolkit
Smart routing across three complementary encryption tools. Pick the right tool based on what needs protecting, apply it, and optionally sign the result.
Tool Selection
| Signal | Tool | Why |
|---|---|---|
Hugo site, markdown content, _index.md cascade, .cryptoid.yaml |
cryptoid | Multi-user/group whole-page encryption integrated with Hugo build |
HTML files, static site output, arbitrary files for web delivery, <pagevault> tags |
pagevault | Section-level or whole-file encryption, self-contained HTML output with viewers |
Offline encryption, signing, key exchange, .gpg files, asymmetric crypto |
gpg | Standard file encryption, detached signatures, public key infrastructure |
Decision Tree
Is the target Hugo MARKDOWN content (files under content/)?
YES -> cryptoid
NO -> Is this HTML, built site output, assets (PDFs, images), or files
meant for browser viewing?
YES -> pagevault
NO -> gpg
Note the Hugo carve-out: cryptoid encrypts markdown content only. Hugo assets (PDFs, images in static/) and built HTML output go to pagevault, even on a Hugo site.
Override: the user may explicitly name a tool regardless of context. Honor that.
Compound Workflows
Some tasks require multiple tools in sequence:
- Encrypt and sign: Encrypt with cryptoid or pagevault first, then
gpg --detach-signthe output - Verify then decrypt:
gpg --verifythe signature, thenpagevault unlockorcryptoid decrypt - Web delivery + archival:
pagevault lockfor browser access,gpg -ethe original for offline backup
cryptoid — Hugo Site Encryption
Encrypts whole markdown pages for Hugo static sites. Multi-user access control with
group-based permissions and directory cascade via _index.md.
Key concepts: .cryptoid.yaml config (users/groups/salt), encrypted: true front matter,
cascade from _index.md, admin group gets universal access, _index.md bodies are encrypted
(front matter stays readable).
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 153 lines · 49 tokens per session scan A dfacf7a818e3
confidential is a skill published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 1,467 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
alive:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
alive:world
The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.
cco-tools
Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.
alive-search
Search across all walnuts -- decisions, people, files, references, insights, log history.