g-telemetry SKILL.md skillA

g-telemetry from onlygian/g-forge is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add onlygian/g-forge/g-telemetry@git:20260829.59c7c63

Pins git:20260829.59c7c63 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
onlygian/g-forge
Path
skills/g-telemetry/SKILL.md
Versions recorded
5
Latest version
git:20260829.59c7c63, committed Aug 29, 2026
First version recorded
Jun 29, 2026
Size
11,359 bytes
Repository stars
4
License
GPL-3.0

Compute the 8 reliability metrics defined in g-docs/telemetry-metrics.md, derive a health profile (stable / cautious / defensive / recovery), and write it to .claude/telemetry-profile for adaptive orchestration in /g-execute and /g-review. Read-only on history; never modifies retros, forecasts, or git state.

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

**Announce:** "Using g-telemetry to compute reliability metrics and derive the project health profile."

You are running a reliability-assessment pass: read accumulated session history, compute 8 metrics, classify the project's current health profile, and persist that profile so downstream skills can adapt.

## Step 1 — Gather inputs

Read in parallel:

- All files in `g-docs/retros/` — for hallucination, review-catch, spec-deviation, retry-dependency signals, and the escalation fallback when `.claude/escalation-log` is absent
- `git log --oneline -200` via Bash — for regression and rework frequency, and for the escalation-frequency denominator
- `git log --stat -30` via Bash — for token-efficiency proxy (diff size)
- `.claude/escalation-log` if it exists — primary source for escalation count (one line per Three-Strikes event)
- `.claude/review-holds` if it exists — running HOLD counter; folds into rework rate per the spec
- `g-docs/telemetry-metrics.md` — the metric definitions (treat as authoritative spec)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add onlygian/g-forge/g-telemetry@sha256:1f47bfe521f2860a

The line at the top of this page pins the label git:20260829.59c7c63, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_l32bkyfbd6cmehkx.svg)](https://markdownregistry.com/a/art_l32bkyfbd6cmehkx)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Jun 29, 2026 and Aug 29, 2026, about one every 15 days.

versioncommittedcommitsizeaudit
git:20260829.59c7c63 latest2026-08-29 59c7c63 11,359 BA view · diff
git:20260828.27146032026-08-28 2714603 8,319 BA view · diff
git:20260811.a8ae21a2026-08-11 a8ae21a 8,110 BA view · diff
git:20260629.6a13b472026-06-29 6a13b47 8,094 BA view · diff
git:20260629.c6dd0722026-06-29 c6dd072 8,087 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (11359 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 link to a raw IP address
  • pass: No script tag

Source

GitHub

onlygian/g-forge · 4 stars · license GPL-3.0 · pushed 2026-10-28 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_l32bkyfbd6cmehkx
GET https://markdownregistry.com/api/v1/resolve?ref=onlygian/g-forge/g-telemetry
GET https://markdownregistry.com/api/v1/blob/1f47bfe521f2860a6d3f904d39c0431455c67b665ae7fd85a9786e72ea42aa8f

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.

More from onlygian/g-forge

g-adr SKILL.md skill
onlygian/g-forge · skills/g-adr/SKILL.md · Capture an architectural decision record. First triages whether the decision merits an ADR or just a one-line entry in…
git:20260902.43671e4 · audit A · 4 stars
g-afk SKILL.md skill
onlygian/g-forge · skills/g-afk/SKILL.md · Autonomous milestone executor. Requires an approved plan. Runs all pending waves and auto-review with no between-step…
git:20260902.43671e4 · audit B · 4 stars
g-align SKILL.md skill
onlygian/g-forge · skills/g-align/SKILL.md · Brief-deviation check. Compares the project's actual trajectory (ROADMAP progress, recent commits, the observer…
git:20260831.81b585b · audit A · 4 stars
g-audit SKILL.md skill
onlygian/g-forge · skills/g-audit/SKILL.md · Full-codebase or targeted code quality audit. Detects SOLID violations, code smells, architectural drift, dead code…
git:20260722.4b86922 · audit A · 4 stars
g-blast-radius SKILL.md skill
onlygian/g-forge · skills/g-blast-radius/SKILL.md · Analyse the blast radius of a planned change. Inputs a file path, feature name, or list of paths from a plan. Outputs…
git:20260628.bdb8cad · audit A · 4 stars
g-brief SKILL.md skill
onlygian/g-forge · skills/g-brief/SKILL.md · Refresh g-docs/project_brief.md as the project evolves — reads current state, asks targeted questions, and updates the…
git:20260722.4b86922 · audit A · 4 stars
g-doc-review SKILL.md skill
onlygian/g-forge · skills/g-doc-review/SKILL.md · Documentation review gate. Dispatches the doc-reviewer agent on the changed file set to check documentation currency…
git:20260902.43671e4 · audit B · 4 stars
g-docs SKILL.md skill
onlygian/g-forge · skills/g-docs/SKILL.md · Documentation audit and generation. Scans for missing or stale code docs, missing README sections, undocumented env…
git:20260722.4b86922 · audit A · 4 stars
g-doctor SKILL.md skill
onlygian/g-forge · skills/g-doctor/SKILL.md · Read-only health diagnostics for G-Forge projects — 25 checks including hook registration, installed-copy drift, Check…
git:20261028.4cf571d · audit A · 4 stars
g-execute SKILL.md skill
onlygian/g-forge · skills/g-execute/SKILL.md · Execute an approved wave plan by dispatching parallel subagents per wave. Use after /g-plan is approved, or to resume a…
git:20261028.4cf571d · audit A · 4 stars
g-forecast SKILL.md skill
onlygian/g-forge · skills/g-forecast/SKILL.md · Run scope-realism analysis and premortem on an approved-or-pending plan. Outputs a complexity score, a quantified…
git:20260902.43671e4 · audit A · 4 stars
g-help SKILL.md skill
onlygian/g-forge · skills/g-help/SKILL.md · Context-aware help. With no argument, reads current project state and tells you where you are and what to do next, plus…
git:20261028.4cf571d · audit A · 4 stars

Every file in onlygian/g-forge

Browse by kind, by grade A, or by owner.