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 skills add davidnichols-ops/trustcard --skill trustcard-operationsgit clone --depth 1 https://github.com/davidnichols-ops/trustcardWrote 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/davidnichols-ops/trustcard/trustcard-operations)<a href="https://agentmods.dev/skills/davidnichols-ops/trustcard/trustcard-operations"><img src="https://agentmods.dev/badge/skills/davidnichols-ops/trustcard/trustcard-operations/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/davidnichols-ops/trustcard/trustcard-operations"><img src="https://agentmods.dev/badge/skills/davidnichols-ops/trustcard/trustcard-operations.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 | $0.00048 | $0.01289 |
| Opus 5.5 | $0.00019 | $0.00516 |
| Sonnet 5.5 | $0.00010 | $0.00258 |
| Haiku 4.5 | $0.00005 | $0.00129 |
Grade A, and why
trustcard-operations 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trustcard operations
Turn the user's requested MCP access into a working, verifiable gate without asking them to write scripts. Preserve the device's existing transport, credentials, runtime and policy. Use the installed Trustcard CLI or operations MCP; this skill contains instructions, not an independent security boundary.
Prerequisite and discovery
This package requires mcp-trustcard 3.2.0-rc.1 or a later compatible release for fleet commands, the console and trustcard-ops. Check the installed CLI's help and package version. Do not assume npm's current stable release contains these features. If using the accompanying release tarball, install that local artifact in an isolated prefix, then use its absolute executable path. Use a supported Node runtime (18 or later); inspect the actual executable instead of assuming a version-manager path works in background services.
Read the relevant client config and preserve existing entries. Never print environment values, bearer tokens, secret files or whole credential-bearing configs. Identify wrapped and direct connections separately. Start with:
mcp-trustcard status --config /absolute/path/client-config.json --json
mcp-trustcard console --config /absolute/path/client-config.json
Fleet operations accept JSON mcpServers or servers configs with supported stdio wrappers. They do not parse Codex/Grok TOML, infer remote gateway ownership, or prove runtime coverage. For client setup and HTTP endpoints read references/clients.md.
Use the operations MCP when available
Configure trustcard-ops --config /absolute/path/client-config.json as a local stdio MCP server. Its config is fixed at startup; tools cannot select arbitrary executable paths or URLs.
tc_status: local inventory and manifest policy. This does not contact upstreams.tc_explain(server, tool): show the decision, required scopes and local override reason. Account for an expired manifest or audit bypass mode before explaining effective access.tc_renew(server): preview renewal against live discovery.tc_reapprove(server): preview reanalysis and policy migration.
What ships with it
2 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.
- yesterday First seen · 78 lines · 48 tokens per session scan A 01e21b2bcbb8
trustcard-operations is a skill published in the GitHub repository davidnichols-ops/trustcard (4 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 1,289 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-15.
Other skills, from other repositories
atrib
Use atrib as the verifiable substrate for memory, reasoning, and getting sharper over time, not as instrumentation that observes you from the outside. atrib gives the agent two cognitive verbs: attest (write: sign an observation, mark a past record's importance, or supersede a prior position) and recall (read: look up…
causallayer-mcp
This skill provides instructions for AI agents interacting with the CausalLayer Model Context Protocol (MCP) server. CausalLayer is a deterministic AI liability apportionment engine. It takes an incident report and mathematically proves which agent, vendor, or operator is liable based on counterfactual do-calculus…
living-stack
Use Living Stack MCP to establish scoped sessions, authorize bounded actions, record evidence, verify claims, checkpoint work, and export signed traces.
verify-mcp-server
Resolve and check MCP servers using MCPLookup's public identity and trust evidence. Use before recommending, installing, or connecting an MCP server; when identifying an official or first-party server; when comparing similarly named servers, packages, repositories, or endpoints; or when a user asks whether an MCP…
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
emem-long-horizon-memory
Keeps an agent's working state in signed emem notes that outlive its context window, so a later session, or the same agent after a reset, picks up from bytes it can verify rather than from a summary it has to believe. Writes and edits notes in the agent's own namespace (ememmemorycreate, strreplace, supersede)…