enterprise-discover
Use when starting enterprise work in a new repo, new worktree, unfamiliar package, or new computer, or whenever commands, paths, conventions, portability, or…
Skill by anotherben
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/anotherben-enterprise-discover
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/enterprise-discover
What's inside
- Skill name
enterprise-discover- Description
- Use when starting enterprise work in a new repo, new worktree, unfamiliar package, or new computer, or whenever commands, paths, conventions, portability, or project traps are not yet known
- License
- MIT
- Instructions
- 62 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (8)
- SKILL.md
- evals.json · evals/
- machine-state-schema.md · references/
- profile-schema.md · references/
- repo-overlay-layout.md · references/
- commit_portable_state.py · scripts/
- generate_repo_overlay.py · scripts/
- validate_overlay_manifest.py · scripts/
SKILL.md (first lines)
# Enterprise Discover Profile the repository before the rest of the enterprise workflow starts guessing, then generate the repo-local overlay skills that travel with the repo. ## Required Approach 1. Start with an indexed repo lookup if available. - if `cortex-engine` or an equivalent repo index exists, use it first - if not available, state that and fall back to direct filesystem search 2. Build committed `.codex/enterprise-state/repo-profile.json`. 3. Build committed `.codex/enterprise-state/repo-traps.json`. 4. Build committed `.codex/enterprise-state/repo-best-practices.json` if current primary-source guidance is needed and available. 5. Build gitignored `.codex/enterprise-state/local-machine.json` for this computer only. 6. Ensure gitignored `.codex/enterprise-state/agent-sessions/` is the only home for in-flight agent workflow state. 7. Start or refresh the current agent session with `python3 tools/enterprise-skills/enterprise/scripts/agent_session.py ensure ...`, then record discover in that session. 8. Generate or refresh `.codex/repo-skills/<repo-family>-enterprise*` using `scripts/generate_repo_overlay.py`. 9. Stage and commit the portable setup artifacts with `scripts/commit_portable_state.py`. 10. State unknowns instead of guessing. ## Minimum Outputs - repo slug and display name - workspace layout and relative source roots - test, build, and lint commands when verified - migration locations if relevant - auth, tenancy, and high-risk domain conventions - dominant file conventions - known structural traps - source-of-truth docs for risky domains - generated repo-local overlay family name - commit sha for the portable setup commit ## Portability Rules - committed profiles must use relative paths and portable command names only - do not commit usernames, absolute paths, secrets, local interpreter shims, or machine-specific install locations - keep machine-only facts in `local-machine.json` - keep live agent workflow state in gitignored `agent-sessions/` - setup is not complete until the portable repo artifacts are committed - if a command cannot be verified, mark it unknown instead of inventing one ## Codex Rules - Use `multi_tool_use.parallel` for independent reads. - If web research is needed, prefer official documentation and current primary sources. - Refresh the repo-local overlay whenever the committed profile materially changes. - Commit only the portable setup artifacts by default: - `.codex/enterprise-state/repo-profile.json` - `.codex/enterprise-state/repo-traps.json` - `.codex/enterprise-state/repo-best-practices.json` when present - `.codex/repo-skills/` - If discover also updated another portable setup file such as `.gitignore`, include it explicitly with `scripts/commit_portable_state.py --extra-path .gitignore`. - Never commit `.codex/enterprise-state/local-machine.json` or `.codex/enterprise-state/agent-sessions/`. ## References - Use [profile-schema.md](references/profile-schema.md) for the committed repo profile shape. - Use [machine-state-schema.md](references/machine-state-schema.md) for machine-only state. - Use [repo-overlay-layout.md](references/repo-overlay-layout.md) for generated skill naming and paths. - Use [agent-session-model.md](../enterprise/references/agent-session-model.md) for agent-bound workflow state.
From anotherben/agentic-governance, MIT.
More from anotherben/agentic-governance
- 0.479score
enterprise
anotherben
Use when starting a feature, significant refactor, enterprise hardening effort, or multi-stage bugfix that needs end-to-end workflow control, portable…
SkillCFreshness: CClaude Code +9 - 0.479score
enterprise-build
anotherben
Use when a locked enterprise contract exists and implementation must proceed through strict TDD, contract traceability, and staged review handoffs
SkillCFreshness: CClaude Code +9 - 0.479score
enterprise-compound
anotherben
Use when verified enterprise work or a resolved debugging session should be captured as searchable institutional knowledge with prevention guidance
SkillCFreshness: CClaude Code +9 - 0.479score
enterprise-contract
anotherben
Use when an enterprise implementation plan exists and work needs a locked contract with postconditions, invariants, consumer mapping, and traceability before…
SkillCFreshness: CClaude Code +9 - 0.479score
enterprise-forge
anotherben
Use when reviewed enterprise work still needs adversarial probing, mechanical checks, and recycle-loop bug closure before final verification
SkillCFreshness: CClaude Code +9 - 0.479score
enterprise-harness
anotherben
Use when enterprise work has been built and reviewed and needs a final mechanical ship gate before merge, install, or release-level signoff
SkillCFreshness: CClaude Code +9 - 0.479score
enterprise-plan
anotherben
Use when an approved enterprise design exists and the next step is to turn it into an exact implementation plan with file paths, task boundaries, and…
SkillCFreshness: CClaude Code +9 - 0.479score
enterprise-pr-review
anotherben
End-to-end PR conversation closer and advisory review harvester for enterprise work.
SkillCFreshness: CClaude Code +9 - 0.479score
enterprise-review
anotherben
Use when enterprise implementation is complete enough for a structured review that separates spec compliance from code quality and classifies drift explicitly
SkillCFreshness: CClaude Code +9 - 0.479score
enterprise-verify
anotherben
Use when enterprise work is about to be declared complete and the claim needs fresh evidence, postcondition tracing, and an explicit proof-scope verdict
SkillCFreshness: CClaude Code +9 - 0.474score
enterprise-stack-review
anotherben
Tech stack decision phase for the enterprise pipeline.
SkillCFreshness: CClaude Code +9 - 0.466score
enterprise-brainstorm
anotherben
Deep enterprise brainstorming that turns vibe-coded ideas into Technical Design Documents.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 4, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/anotherben/agentic-governance
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from anotherben
- 0.534score
deep-think
anotherben
Mandatory read-only pre-action and plan-review protocol for substantive coding, debugging, design, review, refactor, system-analysis, workflow, and…
SkillCFreshness: C★ 7Claude Code +9 - 0.530score
diagnose
anotherben
Use when debugging bugs, failures, regressions, stale proof, recurring whack-a-mole fixes, unclear ownership, poor seams, missing domain boundaries…
SkillCFreshness: C★ 7Claude Code +9 - 0.530score
code-variable-audit
anotherben
Audit pull requests, branches, diffs, or local source files for semantically suspicious variable, identifier, member-access, and payload-field usage.
SkillCFreshness: C★ 7Claude Code +9 - 0.530score
daily-domain-refactor-runner
anotherben
Use when inspecting Helpdesk domains for SRP, README, write-boundary, table ownership, or service-migration opportunities and when running one selected domain…
SkillCFreshness: C★ 7Claude Code +9 - 0.529score
deploy-checklist
anotherben
Use when preparing to deploy code to production, merging to main, running migrations on production databases, or setting environment variables on Render.
SkillCFreshness: C★ 7Claude Code +9 - 0.526score
contract-manager
anotherben
Review plans, fixes, and designs before implementation so code can be built mechanically.
SkillCFreshness: C★ 7Claude Code +9
Cite this page
enterprise-discover skill. Agent Mart. https://agentmart.dev/skills/anotherben-enterprise-discover (last updated 2026-10-24)