| name | endor-agent-kit-setup |
| description | Use when setting up Endor Labs Agent Kit for Codex, checking readiness,
installing or updating bundled Codex custom agents, verifying Endor auth,
or diagnosing missing endorctl, gh, namespace, or toolchain prerequisites.
|
Endor Agent Kit Setup For Codex
Generated for Endor Labs Agent Kit Codex plugin endor-labs-agent-kit v2.1.0.
Bundled Codex Agents And Skills
ai-sast-triage -> endor-ai-sast-triage-agent
cicd-posture -> endor-cicd-posture-agent
dependency-decision-helper -> endor-dependency-decision-helper-agent
endor-troubleshooter -> endor-troubleshooter-agent
findings-browser -> endor-findings-browser-agent
malware-response -> endor-malware-response-agent
package-risk-summary -> endor-package-risk-summary-agent
probe-droid -> endor-probe-droid-agent
remediation-planner -> endor-remediation-planner-agent
repository-dependency-reviewer -> endor-repository-dependency-reviewer-agent
sca-remediation -> endor-sca-remediation-agent
upgrade-impact-analysis -> endor-upgrade-impact-analysis-agent
vulnerability-explainer -> endor-vulnerability-explainer-agent
endor-agent-kit-setup -> endor-agent-kit-setup-agent
Codex Install Commands
Resolve the bundled installer from either the Agent Kit/ai-plugins
checkout root or Codex's plugin cache:
ENDOR_CODEX_INSTALLER="plugins/codex/endor-labs-agent-kit/scripts/install_codex_agents.py"
if [ ! -f "$ENDOR_CODEX_INSTALLER" ]; then
ENDOR_CODEX_INSTALLER="$(find "${CODEX_HOME:-$HOME/.codex}/plugins/cache" -path "*/endor-labs-agent-kit/scripts/install_codex_agents.py" -print -quit)"
fi
test -f "$ENDOR_CODEX_INSTALLER"
Check installed Endor Codex agents and skills:
python "$ENDOR_CODEX_INSTALLER" --status
Move stale Endor Agent Kit plugin-cache copies after user approval:
python "$ENDOR_CODEX_INSTALLER" --purge-stale-plugin-cache --yes
Install or update all bundled Endor Codex agents and skills after user approval:
python "$ENDOR_CODEX_INSTALLER" --install --yes
Install only one surface when diagnosing host discovery:
python "$ENDOR_CODEX_INSTALLER" --install --agents-only --yes
python "$ENDOR_CODEX_INSTALLER" --install --skills-only --yes
Uninstall only Endor Agent Kit-managed Codex agents and skills after user approval:
python "$ENDOR_CODEX_INSTALLER" --uninstall --yes
Endor Agent Kit Setup
Use this setup workflow when the user asks to install, check, update, or remove
Endor Labs Agent Kit plugin support files, or when an Endor Agent Kit workflow
is blocked by missing endorctl, GitHub CLI, authentication, namespace, or
local toolchain readiness.
Setup Contract
Be proactive about checking the environment, but do not make persistent changes
without explicit user approval. Report evidence for each check. Never print
secret values.
Setup may:
- Inspect command availability and versions for
endorctl, gh, git, and
workflow-relevant language tooling.
- Read
ENDOR_NAMESPACE from the current process environment and report it as
namespace provenance when present.
- Safely parse
~/.endorctl/config.yaml for non-secret fields such as
ENDOR_API and ENDOR_NAMESPACE.
- Report the presence of credential fields by key name only.
- Report the presence of
ENDOR_API_CREDENTIALS_* authentication variables by
key name only.
- Run lightweight read-only Endor auth verification when config or credentials
are present.
- Offer re-authentication when verification fails.
- Check
gh authentication and point to official installation guidance.
- Inspect Endor MCP support when a selected workflow needs MCP or the user asks
for MCP setup.
- Offer host-specific Endor MCP configuration only after explaining the exact
file, command, and validation step.
- Install, update, or uninstall host-specific Agent Kit support files only after
explicit approval.
Setup must not:
- Run
endorctl scan.
- Run
endorctl host-check.
- Print
~/.endorctl/config.yaml or secret values.
- Read, cat, source, recurse through, or point
ENDORCTL_CONFIG or
--config-path at tenant-specific, customer-specific, production, backup,
or other non-default Endor config directories.
- Ask the user to paste API keys, API secrets, tokens, or passwords into chat.
- Write
ENDOR_API_CREDENTIALS_KEY or ENDOR_API_CREDENTIALS_SECRET.
- Edit shell profile files such as
.zshrc, .bashrc, or PowerShell profile.
- Install
gh, package managers, language runtimes, Docker, JDKs, or build
tooling.
- Configure MCP globally without explicit user approval. MCP remains opt-in per
recipe/workflow.
Readiness Report
Start with a concise readiness report. Separate configured state from verified
state.
Include these sections when relevant:
- Ready
- Needs action
- Optional checks
- Available fixes
For Endor auth, report sanitized fields only:
Endor config: found
API endpoint: https://api.endorlabs.com
Namespace candidates:
- ENDOR_NAMESPACE: not set
- ~/.endorctl/config.yaml ENDOR_NAMESPACE: example-namespace
Selected namespace: example-namespace from ~/.endorctl/config.yaml
Auth: API credential fields present
Endor auth: verified for namespace example-namespace
Secret values: hidden
If a namespace is missing, say that a namespace is required before live Endor
lookups. If a namespace is detected, let the user use it or override it for the
current workflow.
If ENDOR_NAMESPACE from the current process environment and
~/.endorctl/config.yaml disagree, surface both values and stop before live
Endor lookups. Ask the user which namespace to use for this workflow. Do not
silently trust either value, and do not unset environment variables or edit
config files unless the user explicitly asks for that separate operational
cleanup.
When the user selects or supplies a namespace, later workflow agents must pass
it explicitly with -n <namespace> or --namespace <namespace> for scoped
Endor lookups rather than relying on bare endorctl namespace resolution.
Endor Tooling
If endorctl is missing, offer documented install options in this order:
- Package manager route when available, such as Homebrew or npm.
- Direct binary download with checksum verification.
Only install endorctl after explicit approval. If installing to ~/bin, tell
the user how to update PATH for the current shell. Do not edit shell profiles.
If API credential fields are present, do not run browser auth unless the user
explicitly asks to switch or re-authenticate. If API credential setup is needed,
tell the user to set ENDOR_API_CREDENTIALS_KEY and
ENDOR_API_CREDENTIALS_SECRET through their preferred secure environment
mechanism.
When browser or SSO authentication is requested, confirm the namespace first.
Use non-interactive flags where supported. If multi-tenant selection appears,
summarize the available tenant choices and ask the user before retrying.
Endor MCP
Prefer documented Endor API or endorctl api lookups for workflows that support
them. Configure Endor MCP only when a selected MCP-capable workflow needs it or
the user explicitly asks for it.
The distribution may include ready-to-use Endor MCP config snippets such as
root .mcp.json or Gemini mcpServers metadata. Treat those files as setup
inputs, not permission to start or register MCP without approval.
When MCP setup is requested:
- Check whether
npx is available.
- Check whether
endorctl is available.
- Verify the proposed server command is:
npx -y endorctl ai-tools mcp-server.
- Inspect the host-specific MCP config location or installed plugin metadata.
- If
endor-cli-tools is already registered, report it and ask before
changing anything.
- If it is missing, show the exact config that would be added and ask for
approval before writing host config files.
- After approval and configuration, validate in a fresh host session when the
host supports tool visibility checks.
Do not claim Endor MCP tools are available to a workflow until the host exposes
them in the current session. If MCP tools are unavailable, continue with
CLI-first workflows when they support endorctl api; otherwise record the
missing MCP capability in data_gaps.
GitHub CLI
Check gh auth status when workflows need GitHub evidence, repository
inventory, pull requests, or comments. If gh is missing, provide current
official installation guidance instead of installing it automatically.
Do not manage GitHub token scopes or create personal access tokens. Verify
only the specific read or write capability needed for the selected workflow.
Language Tooling
Detect and report workflow-relevant package managers, language runtimes, and
build tools. Do not install them.
When tooling is missing, report the affected validation step and ask the user to
install it through their team-standard toolchain.
Workflow Safety
Setup never performs remediation, creates branches, opens PRs/MRs, posts
comments, writes Endor policies, or runs scans. Mutating workflows such as SCA
Remediation and AI SAST Triage keep those actions behind their generated agent
approval gates.
Codex-Specific Rules
- Install Codex custom agents globally by default under
${CODEX_HOME:-~/.codex}/agents and bundled user skills under $HOME/.agents/skills.
- Do not write project-local
.codex/agents/ or repo-local .agents/skills/ files unless the user explicitly requests that advanced option.
- Use provenance-gated updates: missing files may be installed; managed stale files may be updated after approval; unknown files or directories must not be overwritten.
- Treat stale Endor Agent Kit plugin-cache warnings from
--status as active-host risk; remove or reinstall the stale package and start a fresh Codex thread before judging agent behavior.
- Use
--purge-stale-plugin-cache --yes only after user approval; it moves stale cache directories to ${CODEX_HOME:-~/.codex}/plugins/cache-backups/.
- Tell the user to start a new Codex thread after installing or updating custom agents or skills.