Monthly Safety Compliance Report (sample)

An example of the deliverable shipped every month on the cc-safe-setup for Teams (Org Guard) tier.

This is a sample for a fictional company. A real report is generated automatically from every repository's settings.json, CLAUDE.md, CI config, and hook execution logs. The repo names, scores, counts, and bypass records below are illustrative — they show the format and the level of detail, not a real organization.

1. Report overview

Organization (fictional)Acme Corp — Product Engineering
Reporting period1–31 May 2026
Repositories covered8 repos (entire GitHub organization)
Developers covered23 (ran Claude Code in the last 30 days)
Intended forSecurity owner / SOC2 evidence / customer security questionnaires
MethodAggregated from npx cc-safe-setup --audit --json per repo plus hook-log analysis (no manual entry)

2. Org-wide safety score

The organization's posture this month, aggregated from every repository's safety score (0–100). It's based on the hooks that are actually in effect per repo, checked mechanically — not on "we think we configured it".

78/100
Org weighted-average score
+6
vs last month (72)
2
repos below baseline
23
developers protected

Your real risk is set by the least-protected repo (the one nobody configured decides the org's effective exposure). This month legacy-billing and data-pipeline are below baseline; the remediation roadmap is in section 6.

3. Per-repository scores

RepositoryScoreGradeCritHighvs last mo.
web-frontend95A00▲ +3
api-core92A01▲ +8
auth-service88B01― 0
mobile-app83B02▲ +5
internal-tools80B02▲ +12
infra-terraform74C03― 0
data-pipeline52C13▼ −4
legacy-billing38F22▼ −6

Grades: A (80+) / B (60+) / C (40+) / F (below 40). Crit and High are counts of open findings at that severity.

4. Incident rule feed shipped this month

Every month we ship a signed rule pack built from newly reported destructive incidents. Each rule is tied to a real, numbered incident and rolled into every repo's baseline within the month — not a generic checklist, but a fast response to what actually happened. This is the value that compounds over time, and it's built from a corpus only we maintain.

RULE-2605-01 — block unrestricted subagent writes

Response to: a helper (subagent) asked to "run 2 commands" rewrote 15 files on its own, including a production migration. At the execution layer this reads agent_id and blocks only subagent-originated writes to high-blast paths (migrations, IaC, .env, production config).

Source incident: #65152 · Applied to: all 8 repos · Severity: Medium

RULE-2605-02 — block collateral wildcard deletes in auto mode

Response to: in auto mode a wildcard delete like *copy* swept up files the user never intended. Blocks absolute-path and home-directory wildcard deletes; lets bounded relative-path deletes through.

Source incident: #64559 · Applied to: all 8 repos · Severity: High

RULE-2605-03 — block prisma db push --accept-data-loss

Response to: a migration-discard flag wiped production data. Hardened to catch --force-reset and --accept-data-loss reliably, even when they appear after a --schema argument.

Source incident: #14411 · Applied to: data-pipeline · Severity: Critical

5. Baseline drift & hook-bypass audit

We turn "it should be working" into "here's the log". This records drift from the org baseline and how often developers bypassed the safety checks (e.g. committing with --no-verify), per repository.

EventRepositoryCountNote
git commit --no-verify (skipped the CI safety gate)legacy-billing7Same developer. Worth a conversation.
Missing baseline hook (destructive-guard not configured)legacy-billingBaseline never applied on clone
Missing baseline hook (secret-guard not configured)data-pipelineConfig drift. Fixed in section 6.
Destructive operations blocked by a hook (working as intended)all repos14Of which: recursive deletes 6 · force pushes 5 · .env commits 3

The last row is "prevented", not "incidents" — evidence for leadership and customers that the safety investment actually fired.

6. Remediation roadmap (recommended by next month)

PriorityTargetRecommended action
Criticallegacy-billingRe-apply the baseline (npx cc-safe-setup --team). This is production billing code; a missing destructive-guard is the top thing to close.
Highdata-pipelineApply secret-guard and roll in the --accept-data-loss block (RULE-2605-03).
Mediumlegacy-billing · 7× --no-verifyReview the practice of skipping the CI gate. If a bypass is ever needed, document an exception process.
Lowinfra-terraformAdd terraform destroy protection to the baseline (currently warn-only).

7. Executive & audit summary

For the period of May 2026, operations-layer safety controls for Claude Code were continuously applied across Acme Corp Product Engineering's 8 repositories and 23 developers. The org weighted-average score improved from 72 to 78, and 14 destructive operations were automatically blocked during the period. Two repositories are below baseline; the section 6 remediation is expected to improve them next month.

This summary is delivered in a form you can attach directly to a SOC2 evidence package, a customer security questionnaire, or a quarterly leadership report.

8. About this sample

This is an example deliverable from the cc-safe-setup for Teams (Org Guard) tier. The core hooks stay free forever (MIT), and the individual --audit score stays free too. The tier only adds what a single developer doesn't need but an organization does: the cross-repo rollup, the monthly incident rule feed, the bypass audit, and a report you can hand over.

The cited incidents (#65152 · #64559 · #14411) are all real, reported GitHub issues. The hook behind each rule is verified live in the cc-safe-setup repository. The scores, counts, and repo names are fictional.

Honestly: this tier isn't built yet — we're gauging demand first (the core hooks are free to use right now). If a shared, enforceable, CI-integrated safety policy would help your team, a 👍 or a one-line comment on the discussion below directly decides what we build first. Indicative price is ~$12 / developer / month, with small teams (≤5) free.

Tell us it'd help — Discussion #632 → Team rollout playbook →