Is compare safe to install?

SaferSkills independently audited compare (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.

CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

100

35.0 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 0 flagged

Securityscore 100 · 0 findings

✓—All security checks passedNo findings in this category for the latest scan.pass

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

skills/compare/SKILL.md · 1 file

skills/compare/SKILL.md2.3 KB · Markdown

name: compare

version: 0.0.5

description: >

Asset-only retrospective. No transcript re-scan, no LLM re-analysis, no HITL.

Triggers: "compare", "review past", "what changed", "self retrospective".

ssl:

scheduling:

anti_triggers:

- ".honne/assets/ 미생성 또는 비어있을 때 (whoami 먼저 실행)"

structural:

scenes:

- "Step 1: Scope HITL"

- "Step 2: Assets presence check"

- "Step 3: Load claims+evolutions"

- "Step 4: Time-bucket grouping"

- "Step 5: Render docs/honne-compare.md"

- "Step 6: Asset immutability check"

branches:

- "Step 2: assets dir absent or empty → print 'No assets yet' + exit 0"

- "Step 5: user requested 'summarize' → cite-bound LLM pass (otherwise pure render)"

resumable: false

logical:

tools: ["bash"]

side_effects:

reads:

- ".honne/assets/*.jsonl"

writes:

- "docs/honne-compare.md # overwrite"

deletes: []

network: []

idempotent: false # summarize branch invokes non-deterministic LLM

rollback: "docs/honne-compare.md 는 .gitignore 대상 — 실행 전 cp 백업 또는 출력 검증 후 수동 삭제."

compare — Read-only Retrospective

Step 1: Scope HITL (one-shot)

Ask: "Retrospective scope — repo or global?"

Step 2: Assets presence check

If .honne/assets/ absent or empty: Print "No assets yet. Run honne first." and exit 0.

Step 3: Load claims + evolutions

bash "${CLAUDE_PLUGIN_ROOT}/scripts/query-assets.sh" \
  --tag "<axis>" --scope "$SCOPE" --type claim --out stdout

bash "${CLAUDE_PLUGIN_ROOT}/scripts/query-assets.sh" \
  --type evolution --scope "$SCOPE" --out stdout

Async wait pattern — use Monitor until-loop, not sleep N && cat:

# ✓ Monitor: until [ -f ".honne/assets/claim.jsonl" ]

Step 4: Time-bucket grouping

Group by axis × recorded_at bucket (YYYY-MM granularity for MVP).

Step 5: Render docs/honne-compare.md (+ stdout)

Format per architecture PRD §4.2 compare Step 6. No LLM unless the user asked for "summarize" — and even then, only cite-bound.

Step 6: Asset immutability check

This skill MUST NOT write to .honne/assets/ or .honne/persona.json. Verify (test): stat -c %Y on assets/*.jsonl before/after unchanged.

compare— agent skill

Is compare safe to install?

compare — Read-only Retrospective

Step 1: Scope HITL (one-shot)

Step 2: Assets presence check

Step 3: Load claims + evolutions

Step 4: Time-bucket grouping

Step 5: Render docs/honne-compare.md (+ stdout)

Step 6: Asset immutability check

Audit the pieces. Scan the whole. Decide.