review-plan-findings-feedback — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited review-plan-findings-feedback (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Review a follow-up feedback file after plan-review findings were addressed. Do not implement code and do not edit the plan. The only possible artifact is a new-findings file.
.ai/impl_plans/<plan-id>-findings-feedback/feedback.md.implementation-plan-review.Infer exactly one plan-id, such as issue-418.
Priority:
.ai/impl_plans/<plan-id>.md..ai/impl_plans/<plan-id>-findings-feedback/feedback.md..ai/impl_plans/<plan-id>-scratchpads/....Confirm .ai/impl_plans/<plan-id>.md exists before proceeding.
Before reading or listing any files under .ai/impl_plans/<plan-id>-findings/, run:
bash .agents/skills/review-plan-findings-feedback/scripts/reset_findings_dir.sh <plan-id>Use the printed absolute directory path for this run's output. If the script exits non-zero, fix the cause and rerun it before doing review work.
Read in full:
.ai/impl_plans/<plan-id>.md.Read targeted evidence as needed:
.cursor/rules/*.mdc files needed to verify whether the feedback and plan edits are correct.Do not open unrelated implementation plans.
For each original finding:
Then scan the edited plan sections for newly introduced or newly exposed issues. Apply the same review standard as implementation-plan-review, but only report findings that are new after the feedback round or still unresolved despite the feedback.
Do not report:
If new findings exist, create exactly one Markdown file:
.ai/impl_plans/<plan-id>-findings/findings.mdThe file must contain only a list of new findings. Do not add an introduction, summary, "no findings" line, or review sections.
Use this item shape:
- **Severity:** Major
**Location:** Phase N / plan section + relevant repo file or rule
**Problem:** What remains wrong or what new problem was introduced.
**Recommendation:** Concrete change to the plan.
**Rationale:** Why it matters.If there are no new findings, do not create any file in the findings directory.
If a findings file was created, reply with only a clickable link to it:
[.ai/impl_plans/<plan-id>-findings/findings.md](.ai/impl_plans/<plan-id>-findings/findings.md)If no new findings were found and every original finding was closed by plan edits, reply exactly:
No new findings.If no new findings were found and at least one original finding was rejected by the feedback but you accept the rejection, reply exactly:
No new findings. Rejections accepted.Do not repeat findings in chat.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.