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/onwardplatforms/infracodebase-mcp/connect-self-hosted-httpsnpx skills add onwardplatforms/infracodebase-mcp --skill connect-self-hosted-httpsgit clone --depth 1 https://github.com/onwardplatforms/infracodebase-mcpWhat 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 | $0.00091 | $0.01976 |
| Opus 5 | $0.00046 | $0.00988 |
| Sonnet 5 | $0.00018 | $0.00395 |
| Haiku 4.5 | $0.00009 | $0.00198 |
Grade A, and why
connect-self-hosted-https 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> **Don't test the cert with `curl`.** On macOS `curl` trusts the system keychain, so How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connect the infracodebase MCP server to a self-hosted HTTPS API
The server takes all configuration from environment variables (or flags) supplied
by the MCP client — there is no init, no auth login, and no stored config file.
Connecting to a self-hosted instance means setting two (sometimes three) env vars in
the client's server definition.
The variables
| Variable | Purpose | Required |
|---|---|---|
INFRACODEBASE_TOKEN |
Personal access token (icb_pat_...) |
Yes |
INFRACODEBASE_API_URL |
Your instance's API base, e.g. https://infra.acme.com/api/v1 |
Yes for self-hosted (defaults to the SaaS) |
NODE_EXTRA_CA_CERTS |
Path to your CA cert — only for HTTPS with a private/self-signed cert | Only if TLS fails |
Step 1 — point at your instance
Use the --env flag (repeatable) on claude mcp add. The -- separates Claude's
flags from the command that launches the server.
Via npx (published package):
claude mcp add infracodebase \
--env INFRACODEBASE_TOKEN=icb_pat_xxx \
--env INFRACODEBASE_API_URL=https://infra.acme.com/api/v1 \
-- npx -y @infracodebase/mcp@latest
From a local clone (after npm install && npm run build):
claude mcp add infracodebase \
--env INFRACODEBASE_TOKEN=icb_pat_xxx \
--env INFRACODEBASE_API_URL=https://localhost:3000/api/v1 \
-- node /abs/path/to/infracodebase-mcp/dist/index.js
Equivalent mcp.json (Claude Desktop / Cursor / etc.):
{
"mcpServers": {
"infracodebase": {
"command": "npx",
"args": ["-y", "@infracodebase/mcp@latest"],
"env": {
"INFRACODEBASE_TOKEN": "icb_pat_xxx",
"INFRACODEBASE_API_URL": "https://infra.acme.com/api/v1"
}
}
}
}
Add --scope user (or set it in user config) to make the server available across all
projects instead of just the current one.
Step 2 — handle the certificate (HTTPS only)
Plain http:// (e.g. http://localhost:3000) needs nothing further — skip this step.
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 · 169 lines · 91 tokens per session scan A e41631b65e2e
connect-self-hosted-https is a skill published in the GitHub repository onwardplatforms/infracodebase-mcp (2 stars, last pushed 8d ago), licensed MIT. It adds 91 tokens to every session and 1,976 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
conducting-cyber-risk-assessment-with-nist-800-30
Conduct a defensible cybersecurity risk assessment using the NIST SP 800-30 Rev 1 methodology: prepare scope and a risk model, identify threat sources and threat events, identify vulnerabilities and predisposing conditions, determine likelihood and impact, compute risk, and communicate results as a prioritized risk…
achieving-cmmc-level-2-compliance
Prepare a defense-contractor environment for CMMC Level 2 certification: scope CUI and FCI, implement the 110 NIST SP 800-171 Rev 2 security requirements across 14 families, compute the SPRS score with the DoD Assessment Methodology, manage a compliant POA&M, and ready the organization for a C3PAO assessment. Use when…
agt-policy-authoring
Create and validate a minimal AGT Copilot CLI policy tailored to the repository being inspected.
compliance
Use when scoping which regulatory frameworks bind a business — SOC 2, ISO 27001, HIPAA, PCI DSS, EU AI Act, DORA, NIS2 — building a control register with owners and evidence, or standing up the cadence that keeps it audit-ready. NOT drafting privacy-policy/ROPA/DPA or ToS text (that is gdpr-privacy, terms-conditions)…
lq-board-document-review
Use when reviewing board-level governance documents — Delegation of Authority policies, charters, board resolutions, related party transaction policies, or committee terms of reference. Produces a structured four-category finding set with tracked changes in Word, a populated Reconciliation Log in Excel, and a draft…
lq-governance-playbook-benchmark
Use when benchmarking a board-level governance document against the LQ Governance Playbook — a Delegation of Authority policy, committee charter, related party transaction framework, or board terms of reference. Produces a classification table (Match / Partial Match / Below Fallback / Red Flag / Omitted) with specific…