ground-claims SKILL.md skillA

ground-claims from max-sixty/tend is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add max-sixty/tend/ground-claims@git:20261027.b6181d7

Pins git:20261027.b6181d7 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
max-sixty/tend
Path
plugins/tend-ci-runner/skills/ground-claims/SKILL.md
Versions recorded
6
Latest version
git:20261027.b6181d7, committed Oct 27, 2026
First version recorded
Sep 18, 2026
Size
16,289 bytes
Repository stars
43
License
MIT

Ground a public claim in evidence. Use before claiming anything about a tool's behavior, an incident, or code you did not run.

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

# Grounded analysis

- [Source evidence for user-facing claims](#source-evidence-for-user-facing-claims)
- [Verifying external-tool behavior](#verifying-external-tool-behavior)
- [Recurring hallucination shapes](#recurring-hallucination-shapes)
- [Transient incidents vs. durable bugs](#transient-incidents-vs-durable-bugs)
- [Who to ask when you can't do it yourself](#who-to-ask-when-you-cant-do-it-yourself)

## Source evidence for user-facing claims

Before posting any specific claim — a configuration snippet, command syntax,
variable name, or API behavior — find the **source text** that confirms it:
documentation, help output, test expectations, or the code implementing the
public interface. Internal implementation code shows what exists internally,
not how it's exposed; read the docs or user-facing layer too.

<example>
<bad reason="Read Rust code showing a 'target' variable and invented $WT_TARGET">

Bad: Saw `extra_vars.push(("target", target_branch))` in Rust source → posted a hook example using `$WT_TARGET` (an environment variable that doesn't exist — hooks use `{{ target }}` Jinja templates).

</bad>
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add max-sixty/tend/ground-claims@sha256:7c80948c65692779

The line at the top of this page pins the label git:20261027.b6181d7, 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_6yqs7gqpxwbynum2.svg)](https://markdownregistry.com/a/art_6yqs7gqpxwbynum2)

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

Versions

The registry has recorded 6 versions of this file, between Sep 18, 2026 and Oct 27, 2026, about one every 8 days.

versioncommittedcommitsizeaudit
git:20261027.b6181d7 latest2026-10-27 b6181d7 16,289 BA view · diff
git:20261002.6fceb2e2026-10-02 6fceb2e 16,287 BA view · diff
git:20260929.bb5ca162026-09-29 bb5ca16 15,649 BA view · diff
git:20260922.a2c2f602026-09-22 a2c2f60 15,463 BA view · diff
git:20260919.ab827ca2026-09-19 ab827ca 14,017 BA view · diff
git:20260918.1ca04b22026-09-18 1ca04b2 12,841 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 (16289 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

max-sixty/tend · 43 stars · license MIT · pushed 2026-11-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_6yqs7gqpxwbynum2
GET https://markdownregistry.com/api/v1/resolve?ref=max-sixty/tend/ground-claims
GET https://markdownregistry.com/api/v1/blob/7c80948c656927799b6c6158f4c05c8e5d966140b460b7c5cb2368729b36cb53

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 max-sixty/tend

release SKILL.md skill
max-sixty/tend · .claude/skills/release/SKILL.md · Tend release workflow. Use when user asks to "do a release", "release a new version", "cut a release", or wants to…
git:20261031.3640369 · audit A · 43 stars
review-reviewers SKILL.md skill
max-sixty/tend · .claude/skills/review-reviewers/SKILL.md · Outcome-based analysis of tend's CI behavior — checks whether tend's outputs were accepted or rejected, escalating to…
git:20261030.54fbddf · audit A · 43 stars
running-tend SKILL.md skill
max-sixty/tend · .claude/skills/running-tend/SKILL.md · Tend-specific instructions for tend CI workflows. Adds non-standard workflow inclusion for usage analysis and repo…
git:20261103.c4d69e0 · audit A · 43 stars
AGENTS.md AGENTS.md file
max-sixty/tend · AGENTS.md
git:20261105.00bed73 · audit A · 43 stars
AGENTS.md@evals AGENTS.md file
max-sixty/tend · evals/AGENTS.md
git:20261026.6313a5e · audit A · 43 stars
running-tend SKILL.md skill
max-sixty/tend · evals/cases/yolo-merge-authority/policies/leaf/.claude/skills/running-tend/SKILL.md · Project-specific instructions loaded by tend workflows alongside AGENTS.md.
git:20261010.8e7e6dd · audit A · 43 stars
debug-tend-run SKILL.md skill
max-sixty/tend · plugins/install-tend/skills/debug-tend-run/SKILL.md · Debugs a tend CI run from its session-log artifacts. Use for run IDs, PR numbers, or questions about what tend did and…
git:20261107.613c326 · audit A · 43 stars
install-tend SKILL.md skill
max-sixty/tend · plugins/install-tend/skills/install-tend/SKILL.md · Installs tend, rotates credentials, repairs failing tend checks, and manages config, secrets, branch protection, and…
git:20261101.b0ca9e7 · audit B · 43 stars
act-in-other-repos SKILL.md skill
max-sixty/tend · plugins/tend-ci-runner/skills/act-in-other-repos/SKILL.md · Act in another repository. Use before filing an issue, commenting, or contributing anywhere other than this repo.
git:20260924.b3c4ba6 · audit A · 43 stars
check-requester-access SKILL.md skill
max-sixty/tend · plugins/tend-ci-runner/skills/check-requester-access/SKILL.md · Check a requester's access tier. Use when a request aims you at someone else's work — close, lock, label, revert…
git:20261010.8e7e6dd · audit A · 43 stars
code-review SKILL.md skill
max-sixty/tend · plugins/tend-ci-runner/skills/code-review/SKILL.md · Structured second pass over a diff — correctness and cleanup angles, a verify pass, ranked findings returned to the…
git:20261004.166792b · audit A · 43 stars
continue-pr SKILL.md skill
max-sixty/tend · plugins/tend-ci-runner/skills/continue-pr/SKILL.md · Continue an unfinished PR with no human author, including red CI and unresolved findings after a prior response or…
git:20261105.00bed73 · audit A · 43 stars

Every file in max-sixty/tend

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