agentleFS
grace-methodgrace-method/grace-plugin/skills/change-assessment/SKILL.md

change-assessment

Skill0 starsChanged 2 months agoMITView on GitHub

Assess any code change request before implementation. Classifies scale (trivial/small/medium/large), applies a sniff test, and routes to the appropriate process depth. Use before accepting any implementation instruction.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Use this skill before accepting implementation work.

    line 12
  2. Distinctive:

    If concerns arise, surface them as an observation, not a hidden veto:

    line 27
  3. Distinctive:

    If constraints force a shortcut, apply the Ideal Solution Pattern:

    line 30

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Change Assessment

Use this skill before accepting implementation work.

Interaction Pattern

  1. Classify the change scale:
    • Trivial: typo, constant, rename -> implement directly
    • Small: simple bug fix, field addition, bounded behavior tweak -> apply sniff test, then implement
    • Medium: new feature, significant behavior change, new integration -> do a lightweight delta review of the existing analysis (or initial business analysis if none exists)
    • Large: cross-cutting change, new subsystem, architectural shift -> do full business analysis before implementation, updating or re-baselining the product graph
  2. For small changes, apply the sniff test:
    • What goal does this serve?
    • Is this treating a symptom or a cause?
    • Will this change make the next change harder or easier?
  3. If concerns arise, surface them as an observation, not a hidden veto:
    • "You asked for X. Before I implement it, I notice [concern]. Would you like me to just make the change, or should we look at the broader picture first?"
  4. If constraints force a shortcut, apply the Ideal Solution Pattern:
    • name the ideal solution
    • record the expedient choice
    • name the gap as intentional debt
  5. Route to the appropriate next step:
    • trivial -> implement directly
    • small -> implement after sniff test
    • medium + existing analysis present -> analysis-review (delta-focused review of the existing analysis)
    • medium + no existing analysis -> business-analysis (initial analysis)
    • large -> business-analysis to update or re-baseline the product graph, then design-review

Output

Produce a brief classification record containing:

  • change scale
  • rationale
  • sniff test answers when applicable
  • routing decision

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.