agentleFS
vectaosporleyvectaosporley/failstop/skills/check-what-the-tool-reads/SKILL.md

check-what-the-tool-reads

Skill0 starsChanged 4 months agoMITView on GitHub

Before quoting a number or state a tool reported, confirm which project, file, or root that tool is actually reading. Trigger when about to repeat a count, status, version, or metric from any status tool, MCP, or command, especially across multiple projects or environments. Prevents repeating a stale or wrong-source figure as current fact.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the source directly before repeating the tool's summary.

    line 23

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Check what the tool reads

The failure this prevents, measured: a status tool reported "265 gaps". The number was repeated four times as current fact before anyone checked which directory the tool was reading. It was the old project. The active project had 2.

The rule

A tool's number is only as current as the thing it points at. Before you quote it, confirm the source.

How

  • A status/MCP tool spans multiple projects or roots? Confirm which one it is bound to right now. A hardcoded root, a stale config, a default path — any of these makes the number describe the wrong thing.
  • The figure looks surprising, or contradicts what you just saw in the files? Trust the files. Read the source directly before repeating the tool's summary.
  • The tool reports a version or identity? Check it matches the project you think you're in. "version": "old-2.0" is the tool telling you it's reading the wrong place.

The tell

You're about to write a specific number — "265 gaps", "0 successes", "14 tools" — that you got from a tool, not from looking. Before it becomes a fact in your answer, confirm the tool is reading what you think it is. One check now prevents a wrong number repeated four times.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.