Hermes ImportsSAFE
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Overview
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
bd656e3e97c4OBSERVED · 2026-09-20What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: hermes-imports description: Hermesデータインポート、マッピング、変換、およびデータインテグリティ検証。 origin: ECC --- # Hermes Imports Use this skill when turning a repeated Hermes workflow into something safe to ship in ECC. Hermes is the operator shell. ECC is the reusable workflow layer. Imports should move stable patterns from Hermes into ECC without moving private state. ## When To Use - A Hermes workflow has repeated enough times to become reusable. - A local operator prompt should become a public ECC skill. - A launch, content, research, or engineering workflow needs sanitized handoff docs. - A workflow mentions local paths, credentials, personal datasets, or private account names that must be removed before publication. ## Import Rules - Convert local paths to repo-relative paths or placeholders. - Replace live account names with role labels such as `operator`, `default profile`, or `workspace owner`. - Describe credential requirements by provider name only. - Keep examples narrow and operational. - Do not ship raw workspace exports, tokens, OAuth files, health data, CRM data, or finance data. - If the workflow requires private state to make sense, keep it local. ## Sanitization Checklist Before committing an imported workflow, scan for: - absolute paths such as `/Users/...` - `~/.hermes` paths unless the doc is explicitly explaining local setup - API keys, tokens, cookies, OAuth files, or bearer strings - phone numbers, private email addresses, and personal contact graphs - client names, family names, or account names that are not already public - revenue, health, or CRM details - raw logs that include tool output from private systems ## Conversion Pattern 1. Identify the repeatable operator loop. 2. Strip private inputs and outputs. 3. Rewrite local paths as repo-relative examples. 4. Turn one-off instructions into a `When To Use` section and a short process. 5. Add concrete output requirements. 6. Run a secret and local-path scan before opening a PR. ## Example: Launch Handoff Local Hermes prompt: ```text Read my local workspace files and finalize launch copy. ``` ECC-safe version: ```text Use the public release pack under docs/releases/<version>/. Return one X thread, one LinkedIn post, one recording checklist, and the missing assets list. ``` ## Example: Quiet-Hours Operator Job Local Hermes job: ```text Run my private inbox, finance, and content checks overnight. ``` ECC-safe version: ```text Describe the scheduler policy, the quiet-hours window, the escalation rules, and the categories of checks. Do not include private data sources or credentials. ``` ## Output Contract Return: - candidate ECC skill name - sanitized workflow summary - required public inputs - private inputs removed - remaining risks - files that should be created or updated
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
bd656e3e97c4full audit observations/trust-audit/skill/affaan-m__hermes-imports.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-20 | bd656e3e97c4 | SAFE | B | 89 | first audit |
Questions
What does the Hermes Imports skill do?
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Is Hermes Imports safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Hermes Imports access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (bd656e3e97c4), read on 2026-09-20. The repository is watched, and a new audit runs when it changes — this is the first audit.