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 adaptocms/adapto-cms-agent-skills/plugin install adaptoWrote 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/adaptocms/adapto-cms-agent-skills/adapto-doctor)<a href="https://agentmods.dev/skills/adaptocms/adapto-cms-agent-skills/adapto-doctor"><img src="https://agentmods.dev/badge/skills/adaptocms/adapto-cms-agent-skills/adapto-doctor/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/adaptocms/adapto-cms-agent-skills/adapto-doctor"><img src="https://agentmods.dev/badge/skills/adaptocms/adapto-cms-agent-skills/adapto-doctor.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 | $0.00069 | $0.02512 |
| Opus 5 | $0.00034 | $0.01256 |
| Sonnet 5 | $0.00014 | $0.00502 |
| Haiku 4.5 | $0.00007 | $0.00251 |
Grade A, and why
adapto-doctor 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 11d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
adapto:doctor
Read-only health check for the Adapto CMS toolchain. It never changes anything — it reports what's wrong and the exact command to fix each item. It ships global + per-repo: run it anywhere to check the environment, or inside a project to also check project wiring.
When to use
- Any Adapto CLI command failed and you're not sure why (auth? tenant? CLI missing?).
- Before
adapto:scaffoldor any mutating skill, to confirm preconditions. - After
adapto auth loginor switching tenants, to confirm the session is good. - Triggers: "adapto doctor", "is my adapto setup ok", "why is adapto failing", "check my adapto environment".
When not to use
- To fix things — doctor only diagnoses. It prints fixes; the user (or another skill) runs them.
- As a precondition gate inside other skills — call the relevant CLI check directly; doctor is for humans.
Inputs
- None required. Optional mode flags on the check script:
--repoforce project checks ·--globalskip them · (default: auto — project checks run if apackage.jsonis present in the cwd).--jsonmachine-readable output.--strictexit non-zero when a check fails (for shell gating). Off by default.
Outputs
- A checklist (✓ pass / ⚠ warn / ✗ fail) with a one-line detail and a fix hint per non-passing item, plus a
pass/warn/failtally. --json:{ ok, mode, checks:[{id,label,status,detail,fix}], summary:{pass,warn,fail} }.- Exit code
0on a successful run (a report was produced) — doctor is a diagnostic, so a failing check is data, not a tool error. Read the JSONokfield (or the✗rows) for health. Pass--strictto make failing checks exit1for shell-level gating.
Checks
Environment (always):
cli_installed—adaptoon PATH (else: install hint).cli_version— version ≥requires.cli(warn if older/unparseable). This is the floor: will the skills run at all.cli_current— the installed CLI vs. the latest release tag (git ls-remote --tagson the CLI repo, not the rate-limited GitHub API). This is drift, not a floor: the CLI is pre-1.0 and its command surface moves between releases, so being behind shows up as a missing flag rather than an obvious "you're old". Behind → warn + the upgrade command, which the agent should offer (a §9 consent gate — it replaces a binary on PATH), never run silently. Never a fail. Offline → warn, same 5s cap as below.pack_current— the installed skill pack vs. the latestmain. The plugin sets noversion, so Claude Code keys its cache on the git commit SHA (one commit = one version); this compares the installed SHA (from Claude Code's owninstalled_plugins.json) againstgit ls-remote <pack repo> refs/heads/main. Behind → warn + the update commands. Omitted entirely in a dev checkout (no install record) and if the pack ever adopts an explicit semver. Network failure is a warn, never a blocker — the call is capped at 5s so a diagnostic can't hang on an unreachable GitHub.auth_valid—adapto auth mesucceeds (shows the account email — identity, not a secret).api_reachable—adapto statussucceeds (gated on auth). A permission/403error on this check is downgraded to a warn, not a fail: auth already proved the backend is reachable, so it's not a blocker for content work.tenant_selected— an active tenant exists viaadapto auth orgs, and its enabled languages are surfaced (this is also the canonical locale list per conventions.md §5). ℹ️ This reports the currently-active tenant; it is not an instruction to use it — work skills must still confirm the working tenant before scoped writes (don't assume the active one — conventions.md §12).
What ships with it
1 file 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.
- 11d ago First seen · 127 lines · 69 tokens per session scan A 6ff9edee5e3a
adapto-doctor is a skill published in the GitHub repository adaptocms/adapto-cms-agent-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 2,512 once invoked, about $0.0003 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
invest
First-time fork users: run the invest-setup skill first to initialize. The main flow lives in this skill (the AI agent uses the CLI/MCP to view the portfolio / run the committee / replay decision history). The Web GUI has been retired (2026-07) — every capability is exposed via CLI subcommands / MCP tools. The backend…
invest-setup
A first-time setup workflow for openInvest, a system for tracking investments and running portfolio analysis.
invest-backup
Back up / restore openInvest's local state — memory/ (holdings, strategy, user profile, committee records, dream logs) + db/ (trade ledger, job run history, market-data cache) + .env (SMTP/API credentials) + userprofile.json. All of this data is .gitignore'd with no historical versions in git, so a single accidental…
okf-frontmatter
Maintain openInvest's docs (docs/wiki chapters + docs/wiki/adr) under Google's Open Knowledge Format (OKF). Two jobs. (1) Teach agents to maintain docs the OKF way — every doc carries a small YAML frontmatter block as the single source of truth (type, title, tags, intent, schemasource, documents); schema details link…
yield-xyz-agentkit-builder
Build applications that integrate with the Yield.xyz APIs — staking, lending, vaults, and RWA across 80+ networks. Generates code covering REST API integration, transaction signing, wallet connection, and fee monetization. Use when user wants to build an app, integrate yield, generate code, or set up a project using…
yield-xyz-agentkit-privy
The Privy connector for the Yield.xyz AgentKit — signs and broadcasts via Privy agentic wallets. Extends the yield-xyz-agentkit skill — that skill discovers yields and builds the unsigned transactions; this one adds Privy wallet creation, policy enforcement, signing, and broadcasting, in autonomous and semi-autonomous…