AGENTS.md + skills MCP with CHP R0 gate and adversary decision tools.
Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.
contract_loadCompile an AGENTS.md operating manual into a structured agent contract:Compile an AGENTS.md operating manual into a structured agent contract:
No input schema was published for this tool.
contract_verificationReturn the verification gates from a project's agent contract — the namedReturn the verification gates from a project's agent contract — the named
No input schema was published for this tool.
skills_listDiscover SKILL.md skills visible from a project root (project-scopeDiscover SKILL.md skills visible from a project root (project-scope
No input schema was published for this tool.
skill_loadLoad the full SKILL.md body for a named skill — the on-demand half ofLoad the full SKILL.md body for a named skill — the on-demand half of
No input schema was published for this tool.
decision_gateRun the Consensus Hardening Protocol R0 gate on a proposed decision: is itRun the Consensus Hardening Protocol R0 gate on a proposed decision: is it
No input schema was published for this tool.
decision_adversaryRun a one-shot Consensus Hardening Protocol adversarial pass against a claimRun a one-shot Consensus Hardening Protocol adversarial pass against a claim
No input schema was published for this tool.
engine_statusHealth/readiness probe for the CHP decision engine (PythonHealth/readiness probe for the CHP decision engine (Python
No input schema was published for this tool.
7 of 7 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
AGENTS.md + skills MCP with CHP R0 gate and adversary decision tools.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
The crawl stopped at the depth-4 limit. Anything below that level was never resolved.
The crawl stopped at the 60-package limit. The rest of the tree was never resolved.
36 more resolved packages are not drawn here (display cap: 24). Every dependency carrying an advisory is drawn regardless of the cap. Full inventory (CycloneDX SBOM)
54 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.
+42 more not listed. The counts by reason above cover all of them.
Not followed: peerDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.