GitEasy: Skill for Claude Code

.claude/skills/provenance-stamping/SKILL.md

provenance-stamping is a skill for Claude Code from greenmtnsun/GitEasy. It costs 107 tokens per session (1,938 once invoked), scanned A, original, MPL-2.0.

A rule for adding source details to the results returned by public commands, such as the tool version, data format version, commit, run identifier, and time when known. These details help identify how a result was produced.

In plain words
What is it for?
Use it when designing or changing public commands that return data and when results may need auditing or reproduction.
Why use it?
It makes results easier to reproduce and investigate later when users need to match an answer to the exact code and format that produced it.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is greenmtnsun/GitEasy's own configuration. It tells Claude Code how to work on GitEasy itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything GitEasy configures →

Reuse

Borrowing it

Nothing to install: this file belongs to greenmtnsun/GitEasy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/greenmtnsun/GitEasy/main/.claude/skills/provenance-stamping/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/greenmtnsun/GitEasy

Made for: Claude Code.

Wrote 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.

agentmods badge for provenance-stamping

README.md
[![agentmods](https://agentmods.dev/badge/skills/greenmtnsun/giteasy/provenance-stamping/github.svg)](https://agentmods.dev/skills/greenmtnsun/giteasy/provenance-stamping)
Your own site
<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/provenance-stamping"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/provenance-stamping/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.

agentmods 80×15 button for provenance-stamping

Your own site · 80×15
<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/provenance-stamping"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/provenance-stamping.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,938 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00107 $0.01938
Opus 5.5 $0.00043 $0.00775
Sonnet 5.5 $0.00021 $0.00388
Haiku 4.5 $0.00011 $0.00194

Measured today against content hash 6a71d31fdca7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

provenance-stamping 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 today.

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.

.claude/skills/provenance-stamping/SKILL.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

See also: function-design for the public-surface result shape. software-creation §4 for the structured-result contract. air-gap-discipline for the no-host-name rule the stamp must respect. module-suite for the JSON schema this nests inside.

Provenance stamping — the reproducibility moat

Most PowerShell modules return data and call it done. The user gets numbers, but no way to prove which version of the tool produced them, against which schema, on which commit. When that user is an auditor, a regulator, or a customer reproducing a finding six months later, the gap matters.

This skill encodes the rule that lean toward stamping every public command's result with provenance. It is not yet a hard line (some commands are too lightweight to bother), but it is the suite's distinctive bar.

What goes into a provenance stamp

A Provenance field on the structured result, populated with the values that are knowable at runtime:

$stamp = Get-SbvProvenance -CommandName $MyInvocation.MyCommand.Name -SchemaRevision '1.0'

return [pscustomobject]@{
    Status        = 'Succeeded'
    Outcome       = "Validated 47 backups across 3 instances"
    ErrorCategory = 'None'

    # function-specific result data
    BackupCount   = 47
    InstanceCount = 3

    # provenance stamp (helper defined below; null-safe)
    Provenance    = $stamp
}

Stamp on success and failure paths both. The structured-result rule (per software-creation §4) says every return path returns a result — provenance follows the same rule. An auditor reviewing a HandledError result needs the same provenance as a Succeeded result.

Required fields (when the stamp is present):

  • Command — the function name as PowerShell sees it.
  • ModuleVersion — the importing module's version string. From (Get-Module $MyModuleName).Version.
  • SchemaRevision — the JSON-schema version this command's output conforms to. String, semver-ish (1.0, 1.1, 2.0). Bumped when the result shape changes.
  • RunId — a GUID generated per invocation. Lets a user correlate logs, results, and downstream artifacts that all stem from the same run.
  • TimestampUtc — ISO 8601 UTC. Always UTC; never local time, never an offset (air-gap rule — local time leaks the host's locale).

Read the full file on GitHub · 166 lines

Changes

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.

  1. today First seen · 166 lines · 107 tokens per session scan A 6a71d31fdca7

Subscribe to this mod's changes

provenance-stamping is a skill published in the GitHub repository greenmtnsun/GitEasy (1 stars, last pushed yesterday), licensed MPL-2.0. It adds 107 tokens to every session and 1,938 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-11-18.

Related

provenance-stamping compared with skills from other repositories

provenance-stamping next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
provenance-stampinggreenmtnsun/GitEasySkill1yesterdayMPL-2.0A107Claude Code
systematic-debuggingopen-metadata/OpenMetadataSkill16ktodayApache-2.0A37Claude Code
log-error-digestzebbern/claude-code-guideSkill4.7kyesterdayMITA71Claude Code, Codex
observability-audit-sessionsIBM/mcp-context-forgeSkill4.9ktodayApache-2.0A64Claude Code, Codex
cwv-optimizeradobe/skillsSkill333todayApache-2.0A112Claude Code
ci-fixersipyourdrink-ltd/bernsteinSkill1.2ktodayApache-2.0A15Claude Code, Codex
diagnosing-missing-recordingsPostHog/posthogSkill41ktodaynoneA76Claude Code, Codex