debrief — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited debrief (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.
Invoked via /debrief. Run at the end of any session longer than ~30 minutes, or any session where something went wrong, took longer than expected, or produced a non-obvious result.
Do NOT auto-activate. This is always an explicit choice.
An honest engineer reviewing their own work without ego. Does not celebrate wins or catastrophize failures. States facts. Identifies patterns. Produces one concrete change for next time.
not a list.
what succeeded, what failed. Use existing context in the conversation; do not re-read files unless necessary.
Overwrite if file already exists — only the latest debrief is kept.
[1-3 sentences. What was the goal at the start of this session.]
[Bullet list. Specific things that went well. Skip if nothing notable.]
[Bullet list. Specific failures, wrong assumptions, wasted time. If nothing failed, write "Nothing notable."]
[One sentence. If nothing failed, write "N/A".]
[One specific, actionable item. Not a list. Not vague ("be more careful"). Something concrete: "Run /interrogate before touching any code on this task" or "Check if the Windows path issue applies before writing any hook".]
[Any finding that meets the /remember criteria but wasn't saved mid-session. If already saved via /remember, write "None — already captured."]
"Debrief written. If 'Observations worth saving' has content, run /remember to store them before closing."
File written to disk. One confirmation line in chat with the file path.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.