self-reflect — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited self-reflect (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.
Reflect on the user themselves — leadership, behavior, fulfillment, calendar — and capture the result to ~/bettersense-work-reflections/self/reflections.md. The shape mirrors stakeholder-reflect; the difference is the audience and the question pool.
If the user says "stop", "exit", "I'm done", "that's enough", "pause", or similar — end the session immediately and write whatever has been captured so far. Don't push for more.
In the opening message, add one short sentence: "You can say 'stop' at any time and we'll save what we have."
If ~/bettersense-work-reflections/self/reflections.md doesn't exist:
self/ directory under $BETTERSENSE_WORK_REFLECTIONS_HOME.reflections.md with this frontmatter: ---
subject: self
since: 2026-05-01
---
# Self-reflections
<!-- The self-reflect skill appends per-question entries below this line. -->If ~/bettersense-work-reflections/ itself doesn't exist, hand off to stakeholder-register first — that skill owns the root setup and the privacy warning.
Filter questions.json (loaded from the stakeholder-reflect skill folder) to questions where stakeholder_categories includes self. The pool spans three families:
Default picker, when no specific topic given:
stakeholder-reflect: days_since_last / cadence_days.Show the picks before drilling in:
"Here's what feels worth thinking about: 1) How well have you managed your time and energy recently? (biweekly cadence, last logged 3 weeks ago) 2) How are you handling feedback? (monthly cadence, never logged). Sound right?"
If the user named a topic ("specifically I want to think about advocating for myself"), skip the picker.
Same shape as stakeholder-reflect, with self-specific adaptations:
Append to ~/bettersense-work-reflections/self/reflections.md in the same per-question / per-date structure as stakeholder files.
## How well have you managed your time and energy recently? [current-role, biweekly]
### 2026-05-01
Calendar over the last 2 weeks: 31 hrs of meetings (target was ≤24). Of those,
6 hrs were optional that I could have skipped. Energy: noticeably lower in the
afternoons; I'm protecting mornings well but burning the back half of the day
in low-stakes syncs.
Action: cancel the standing Thursday product review I haven't actively contributed
to in 5 weeks. Block 2-4pm Wednesdays for deep work and treat as inviolable.Self-reflection entries should produce actions or commitments more often than stakeholder entries do — because the user is the only person who can act on them. Encourage this; write the action down explicitly.
stakeholder-reflect or feedback-frameworks.decision-log.stakeholder-synthesize over the self file with that lens.Don't force these. Most self-reflection sessions just need to land cleanly.
compensation or advocating for yourself or handling feedback, that pattern is itself reflective material. Surface it gently.stakeholder-synthesize on their self file once a month or so. The compounding insight is in the rereading, not the writing.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.