palinode-session — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited palinode-session (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.
This skill keeps your AI agent's memory fresh across coding sessions using Palinode MCP tools.
Search for prior context before beginning work:
palinode_search(query="[current project or task description]", limit=5)Review results and reference relevant decisions or blockers from previous sessions.
After each major milestone, save the outcome:
palinode_save(
content="[what was accomplished and why]",
type="Decision", # or "Insight" for reusable lessons
project="[project-slug]"
)If actively working and 30+ minutes since last palinode_save, save a brief progress note:
palinode_save(
content="Progress: [what's been done so far, what's next]",
type="ProjectSnapshot"
)Before the user exits, capture the session:
palinode_session_end(
summary="[1-2 sentence summary of accomplishments]",
decisions=["decision 1 with rationale", "decision 2"],
blockers=["open question or next step"],
project="[project-slug]"
)| Tool | When |
|---|---|
palinode_search | Start of session, or "what do we know about X" |
palinode_save | Milestones, decisions, insights, progress |
palinode_session_end | End of session — structured summary |
palinode_diff | "What changed recently?" |
palinode_blame | "When was this decided?" |
palinode_trigger | Register auto-recall for recurring topics |
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.