agentleFS
clonable-edenclonable-eden/cekernel/skills/probe/SKILL.md

probe

Skill17 starsChanged 8 months agoMITView on GitHub

Diagnostic probe for namespace detection. Tests file-based detection (D2) vs LLM-based detection.

16 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use triage and review.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Google CloudSkill

    triage

    Gather context on a change or bug and plan the implementation.

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 0 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Check whether the skill was invoked with a namespace prefix (e.g., cekernel:probe vs probe).

    line 17
  2. Very specific:

    If namespaced (plugin mode): LLM_DETECTED_NS=cekernel

    line 19
  3. Very specific:

    If not namespaced (local mode): LLM_DETECTED_NS=local

    line 20
  4. Very specific:

    Read skills/references/namespace-detection.md from the repository root ($(git rev-parse …

    line 31
  5. Very specific:

    If CEKERNEL_NS=local: FILE_DETECTED_NS="local", CEKERNEL_AGENT_PROBE="probe"

    line 34

“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “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

/probe

Diagnostic skill to verify D2 (file-based namespace detection) from ADR-0009.

Workflow

Step 1: LLM-based Detection (Current Method)

Determine whether cekernel is running as a plugin or locally by checking how this skill was invoked.

Check whether the skill was invoked with a namespace prefix (e.g., cekernel:probe vs probe).

  • If namespaced (plugin mode): LLM_DETECTED_NS=cekernel
  • If not namespaced (local mode): LLM_DETECTED_NS=local

Report:

[LLM Detection] namespace = <LLM_DETECTED_NS>
[LLM Detection] reason = <how you determined the namespace>

Step 2: File-based Detection (D2 — ADR-0009)

  1. Read skills/references/namespace-detection.md from the repository root ($(git rev-parse --show-toplevel)/skills/references/namespace-detection.md). If the Read fails (file not found), you are in plugin mode.
  2. Execute the detection Bash snippet from the reference file.
  3. Map the result for probe reporting:
    • If CEKERNEL_NS=local: FILE_DETECTED_NS="local", CEKERNEL_AGENT_PROBE="probe"
    • If CEKERNEL_NS=plugin: FILE_DETECTED_NS="cekernel", CEKERNEL_AGENT_PROBE="cekernel:probe"

Step 3: Launch Probe Agent

Using the agent name determined by the file-based detection (Step 2), launch the probe agent:

  • subagent_type: Use CEKERNEL_AGENT_PROBE from Step 2
  • prompt: "Report what you observe. Run the file-based namespace detection from your own context and return the results."

Step 4: Report

Present a comparison table:

## Probe Results

| Method        | Detected Namespace | Agent Name     |
|---------------|-------------------|----------------|
| LLM-based     | <LLM result>      | <agent name>   |
| File-based    | <File result>     | <agent name>   |
| Agent (D2)    | <Agent result>    | <agent name>   |

### Consistency
- LLM vs File: <match/mismatch>
- File vs Agent: <match/mismatch>

### Conclusion
<Whether D2 file-based detection produces correct results in this context>

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.