token-usage-audit SKILL.md skillB
token-usage-audit from edge-city/agentvillage is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add edge-city/agentvillage/token-usage-audit@git:20261005.2ef2194Pins git:20261005.2ef2194 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- edge-city/agentvillage
- Path
skills/token-usage-audit/SKILL.md- Versions recorded
- 3
- Latest version
- git:20261005.2ef2194, committed Oct 5, 2026
- First version recorded
- Jun 22, 2026
- Size
- 3,353 bytes
- Repository stars
- 21
- License
- MIT
Deterministic tenant-local token usage audit for AgentVillage Hermes installs. When explicitly enabled, runs as a script cron and wakes the agent only when a clear actionable token-spend driver is found.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Token Usage Audit This skill owns the local token usage audit cron. It is disabled by default and is operational plumbing for the resident's agent, not a chat skill the agent should mention by name. ## What It Does The script at `scripts/audit_token_usage.py` reads only tenant-local operational metadata: - Hermes dashboard session summaries from `http://127.0.0.1:9119/api/sessions?limit=500` - local cron metadata from `cron/jobs.json` - metadata-like local JSON/JSONL files only as a fallback when dashboard usage is unavailable It does not call an LLM. It does not emit raw message content, prompts, raw session ids, private hosts, secrets, env values, or profile/memory prose. Session ids are used only for in-process grouping and become ordinal refs like `session_001`. ## Cron Contract When explicitly enabled with `--token-usage-audit-cron "<expr>"` or `TOKEN_USAGE_AUDIT_CRON="<expr>"`, the AgentVillage installer creates one Hermes cron: - name: `Edge — token usage audit` - schedule: the configured cron expression - delivery: Telegram only after the script wake gate returns `wakeAgent:true` - skill: `token-usage-audit` …
Read the whole file at its exact version.
How to install
mdr add edge-city/agentvillage/token-usage-audit@sha256:1925fe9d34b30810The line at the top of this page pins the label git:20261005.2ef2194, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_dlwcoqoaqiefdwba)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Jun 22, 2026 and Oct 5, 2026, about one every 52 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261005.2ef2194 latest | 2026-10-05 | 2ef2194 | 3,353 B | B | view · diff |
| git:20260623.66b5804 | 2026-06-23 | 66b5804 | 2,996 B | B | view · diff |
| git:20260622.c2c6e84 | 2026-06-22 | c2c6e84 | 2,794 B | B | view |
Audit of the latest version
- fail: No link to a raw IP address (matched: http://127.0.0.1:9119)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3353 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No script tag
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
edge-city/agentvillage · 21 stars · license MIT · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_dlwcoqoaqiefdwba GET https://markdownregistry.com/api/v1/resolve?ref=edge-city/agentvillage/token-usage-audit GET https://markdownregistry.com/api/v1/blob/1925fe9d34b308108d3754a206c0e44da0c60e1215569d967f7f48f9fdb96973
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.