fetch-plan — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited fetch-plan (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.
Use this skill to reopen an existing plan created with the planning-mode/planning skill's folder structure.
{repo root}/.ai/planning/{yyyy-mm-dd} {task name}plan.mdprogress.mdfindings.mdquestions.md{repo root}/.ai/planning/ls "{repo root}/.ai/planning/" via Bash to list the plan folders since Glob fails to match directories on WindowsExample:
2026-03-20 refactor auth flow2026-03-18 add retry metricsIf no folders exist, tell the user no saved plans were found and suggest creating one with the planning-mode or planning skill.
Prompt the user to reply with either:
Selection rules:
After the user selects a plan, read the available planning documents from that folder.
Read in this order:
plan.mdprogress.md (if it exists)findings.mdquestions.mdOnly read files that exist. If plan.md is missing, say the plan is incomplete and continue with any other available docs.
Summarise the plan's implementation status using only the loaded docs.
Base the status on:
plan.md phase statuses and current phaseprogress.md latest actions and test results (only for multi-phase plans)findings.md blockers, issues, and decisionsquestions.md unresolved questions or missing user answersPrefer plain labels such as:
IncompleteNot startedIn progressBlockedCompleteUnknownWhen reporting back:
After summarising status, prompt the user for the next step. Offer concise options such as:
If the user chooses a follow-on action, continue from the selected plan rather than re-listing plans.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.