Install
$ agentstack add skill-baobao2333-prd-agent-kit-prd-06-admin-config ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
PRD Admin Config
Purpose
Define backend and operations controls only when they are required for launch, safety, or maintainability.
The default stance is conservative: no admin feature should be added unless it protects launch, reduces real operational risk, or is explicitly required by the business.
Inputs
- Business boundary.
- Rule model.
- Page and flow specs.
- Known operations process, if available.
Process
- Identify operations actions required for this version.
- Identify configuration values that cannot safely be hardcoded.
- Identify emergency controls.
- Identify admin validation and operation logs.
- Split admin requirements into
Must-have,Can hardcode this version, andLater.
Admin config rules
- Do not add a config item just because it might be useful someday.
- For every config item, explain the cost of not having it.
- Prefer hardcoded defaults when the value is stable and the launch risk is low.
- Add operation logs when manual actions can affect user rights, money, resources, rankings, or eligibility.
- If operations can misconfigure something harmful, specify validation or confirmation.
- If this version does not need admin or operations controls, say so explicitly and keep the artifact short.
- Do not fill admin tables with speculative modules just to make the section look complete.
- Do not create an admin page merely because a value exists. A page is justified only when a named operator must inspect or change the value during launch, rollback, compliance review, or routine operations.
- If a value is still a product, data, legal, or technical decision, do not mark it as configurable as a way to postpone the decision. Choose a conservative default when responsible; otherwise send it back to the owning stage.
- Prefer emergency kill switches and narrow safety controls over broad manual tuning surfaces.
Challenge pass
Before handing off to data and acceptance:
- For each config item, ask whether the feature can launch safely with a hardcoded value.
- For each admin page or module, name the real operator action it enables.
- For each manual action, name the harm caused by a wrong operation.
- Delete or defer any config whose main purpose is "future flexibility".
- If an admin item exists because a rule is undecided, return to
prd-03-rule-modelerorprd-02-business-boundaryinstead of adding a setting. If the decision cannot be resolved from existing evidence with high confidence, ask the user before handing off.
Output format
# 05 Admin & Operations Config: {Feature Name}
## 1. Admin necessity summary
| Area | Needed this version? | Reason |
|---|---:|---|
## 2. Configuration items
| Config item | Must-have? | Default value | Allowed values | Validation | Not having it means |
|---|---:|---|---|---|---|
## 3. Operations actions
| Action | Operator role | Condition | Result | Needs log? | Needs confirmation? |
|---|---|---|---|---:|---:|
## 4. Emergency controls
| Control | Trigger to use | Result | Risk |
|---|---|---|---|
## 5. Admin pages / modules
| Module | Purpose | Fields | Actions | Priority |
|---|---|---|---|---|
If no admin page is required, write: `No dedicated admin page is needed this version. Required operations are handled by existing tools or hardcoded launch configuration.`
## 6. Can be hardcoded this version
| Item | Why hardcoding is acceptable | Revisit trigger |
|---|---|---|
## 7. Handoff to next stage
Recommended next skill: `prd-07-data-acceptance`
Definition of done
The admin config spec is complete when operations can safely run the feature without the PRD turning into a fake “everything configurable” system.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: baobao2333
- Source: baobao2333/prd-agent-kit
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.