Install
$ agentstack add skill-openplanr-openplanr-planr-challenger-review ✓ 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
Challenger review (independent-challenge)
Test only claims that could change a decision. A careful advisor note may pass without an exception; do not create objections merely to make the review look busy.
Context
Use `, , , and . Inspect the available ceo.md, cto.md, cpo.md, cmo.md, and coo.md notes after the advisor pass. Do not read chair.md or board-report.md. Use the selected roster in the scope or brief: an intentionally unselected lens is omitted by scope`, not unavailable, and creates no gap by itself. If a selected advisor note is unavailable, record the decision impact rather than reconstructing that lens.
Write only ``.
Material exceptions
Report an exception when:
- a consequential claim lacks support or conflicts with stronger project context;
- multiple advisors repeat the same weak assumption as corroboration;
- a realistic alternative or dependency is missing;
- material downside or irreversibility is absent;
- confidence or comparative language exceeds the available context; or
- relevant qualitative context was dismissed only because ideal metrics were unavailable.
Do not challenge tone, formatting, harmless omissions, or a careful Not established statement. Open original project sources only when needed to test a targeted material claim.
File contract
# Challenger review — independent-challenge
> **Contract:** operate-review-quality-contract@2.0.0
> **Verdict:** holds | holds with exceptions | not decision-ready
> **Bottom line:**
## Material exceptions
### X1 —
- **Target:** `#`
- **Type:** unsupported | contradicted | correlated reasoning | missing alternative | unpriced downside | overconfident
- **Decision impact:**
- **Challenge:**
- **Sources:**
- **Resolution:**
## Decisions that still hold
-
## Risks and dissent
- **Dissent:**
- **Resolution condition:**
## Decision-changing gaps
-
Do not reproduce complete source inventories, the entire question rubric, or a second strategy review. The Chair needs exceptions, surviving decisions, dissent, and resolution conditions.
Optional quality check and return
When available, use this as a structural quality check:
node "/scripts/validate-note.mjs" "" --profile challenger --contract-version 2.0.0 --json
Use diagnostics when useful and report any remaining structural issue.
Return verdict, exception count, dissent count, output path, and any unresolved issue in at most five lines.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: openplanr
- Source: openplanr/OpenPlanr
- License: MIT
- Homepage: https://openplanr.dev
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.