Add .claude/scripts/log-skill-error.sh — the canonical agent error log helper
(writes errorlog.md in DATE | MACHINE | skill | [type] error format, soft-fails).
Three categories: execution failures (default), user corrections (--correction),
and preventable self-inflicted friction (--friction; cite ref= when it repeats a
documented gotcha). Goal: stop paying tokens twice for the same avoidable mistake.
- CLAUDE.md: make logging mandatory for all skills + corrections + friction.
- skill-creator: new skills must wire in the helper (guidance + checklist).
- Retrofit every skill script's genuine failure branches to call the helper
(b2/bitdefender/mailprotector/packetdial/coord python CLIs; remediation-tool
+ onboard365 bash; vault, rmm-auth, post-bot-alert, agy, grok, 1password,
run-onboarding-diagnostic). Handled conditions + self-tests left alone.
- errorlog.md: broaden header to cover skills + harness + corrections; seed this
session's corrections (INKY, Mail.Send token-audience, omnibox-strictness) and
friction (git-bash /tmp, env-persistence, argv-limit, PowerShell var-case).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Several bugs found and fixed during live testing against the ACG GravityZone
tenant:
- security_sweep_all_clients: iterate each company (the companies container is
not a valid endpoint parent; passing it 400'd the whole sweep)
- list_quarantine: use service-scoped path quarantine/computers with companyId
(bare quarantine module 404'd; param is companyId not parentId)
- rename GZEndpointSummary.detection_active -> threat_detected with corrected
semantics (True = active threat, tracks with infected; not an engine-on flag)
- status: readable sectioned table renderer for the nested apiKey/license dict
- portable CLAUDETOOLS_ROOT resolution (derive from file path, not a Windows
literal) so it works on the Mac/Linux fleet
Adds scripts/selftest.py: a 29-check read-only harness (all passing) covering
every read command, --json, error exit codes, and destructive-action gating.
EDR/incident commands (blocklist, isolate/unisolate, blocklist-add/remove) and
raw destructive-method gating are included from this session's work.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- raw now refuses destructive methods (delete/uninstall/remove/reconfigure)
without --confirm (it previously bypassed all gating)
- --json is now accepted after the subcommand (shared via a common parent
parser), matching the documented usage
- drop a placeholder-less f-string
- SKILL.md: document raw gating + that raw echoes upstream responses verbatim
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds a /bitdefender skill that drives the ACG GravityZone partner tenant
via the JSON-RPC Public API. Read + management ops (companies, endpoints,
live security sweep, policies [read-only/shallow], packages, quarantine,
scans, groups, move/delete). Identity-tier JSON cache (24h TTL,
--refresh); volatile status is always pulled live, never cached.
Security hardening: API key loaded from SOPS vault at runtime (never on
disk/logs/argv/cache); destructive deletes gated behind --confirm; `raw`
also gates destructive methods; upstream error bodies truncated. UNVERIFIED
API methods reachable only via `raw`. Reuses the auth/JSON-RPC pattern from
api/services/gravityzone_service.py.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
