Borrowing it
Nothing to install: this file belongs to charliehzm/medharness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/charliehzm/medharness/main/.claude/skills/audit-snapshot/SKILL.mdgit clone --depth 1 https://github.com/charliehzm/medharnessWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/charliehzm/medharness/audit-snapshot)<a href="https://agentmods.dev/skills/charliehzm/medharness/audit-snapshot"><img src="https://agentmods.dev/badge/skills/charliehzm/medharness/audit-snapshot/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/charliehzm/medharness/audit-snapshot"><img src="https://agentmods.dev/badge/skills/charliehzm/medharness/audit-snapshot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00235 | $0.02454 |
| Opus 5 | $0.00118 | $0.01227 |
| Sonnet 5 | $0.00047 | $0.00491 |
| Haiku 4.5 | $0.00023 | $0.00245 |
Grade A, and why
audit-snapshot scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Snapshot (Step 12)
The final gate. After this skill runs, the change is frozen, replayable, and regulator-defensible for 6 years.
Core mental model
A bundle is not "all the files we had lying around" — it is a time capsule that, opened by a stranger 4 years from now during a regulatory audit, must allow them to:
- Reconstruct what the AI did — every prompt, every model, every tool call
- Reconstruct what the code became — base commit + diff, with hashes
- Reconstruct what the data was — synthetic fixtures + fingerprints, no real patients
- Reconstruct who approved what — signatures + compliance report
- Verify nothing has been tampered with — hash chain + WORM ROOT_SHA256
If a stranger cannot do this in 4 hours, the bundle is invalid.
What this skill produces
<artifact-storage>/AUDIT_BUNDLE_<change-id>_<archived_at>.tar.gz— the canonical bundle (structure defined in openspec/templates/AUDIT_BUNDLE.spec.md)- WORM record in
mcp-audit-logwith ROOT_SHA256, change_id, archived_at, signers - Optional: a one-page
archive_summary.mdfor stakeholder readout
When NOT to use this skill
Skip for:
- Mid-change snapshots (no concept of mid-archive — bundles are final)
- Changes that haven't passed Step 10 with High = 0
- Pure documentation-only changes (still log an L1 lightweight entry, but skip full bundle if the org policy permits — usually it doesn't, default to full)
Active context bundle
Always load first
- This
SKILL.md openspec/templates/AUDIT_BUNDLE.spec.md— canonical structureopenspec/templates/LINEAGE_GRAPH.schema.json— invariants to enforcereference/hash-chain-protocol.md— exact hash computation order
Load on demand
reference/replay-sanity-check.md— self-test routine before sealingreference/encryption-protocol.md— for desensitize_map.json.encreference/signature-protocol.md— committee signatures (M3+)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 200 lines · 235 tokens per session scan A 3def05b51d95
audit-snapshot is a skill published in the GitHub repository charliehzm/medharness (86 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 235 tokens to every session and 2,454 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
hipaa-review
Performs a HIPAA Security Rule compliance review against all Administrative, Physical, and Technical Safeguards defined in 45 CFR Part 164, Subpart C. Auto-invoked when discussing healthcare data security, ePHI protection, HIPAA audit readiness, or business associate compliance. Evaluates required and addressable…
Healthcare Compliance
HIPAA compliance, healthcare regulations, privacy and security standards for medical organizations and providers.
compliance
Use when scoping which regulatory frameworks bind a business — SOC 2, ISO 27001, HIPAA, PCI DSS, EU AI Act, DORA, NIS2 — building a control register with owners and evidence, or standing up the cadence that keeps it audit-ready. NOT drafting privacy-policy/ROPA/DPA or ToS text (that is gdpr-privacy, terms-conditions)…
performing-soc2-type2-audit-preparation
Automates SOC 2 Type II audit preparation including gap assessment against AICPA Trust Services Criteria (CC1-CC9), evidence collection from cloud providers and identity systems, control testing validation, remediation tracking, and continuous compliance monitoring. Covers all five TSC categories (Security…
akf-trust-metadata-v2
AKF — The AI Native File Format workflow skill. Use this skill when the user needs The AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. Embeds into 20+ formats (DOCX, PDF, images, code). EU AI Act, SOX, HIPAA auditing and the operator should preserve…
compliance-audit
Regulatory compliance auditing across GDPR, HIPAA, PCI DSS, SOC 2, and ISO frameworks with automated evidence collection and gap analysis. Use when conducting compliance assessments, preparing for certifications, or implementing regulatory controls.