agent-dx-cli
Skill14 starsChanged 22 days agoApache-2.0View on GitHub
Designs, reviews, and refactors CLIs for AI agents. Use when building Agent DX CLIs or checking existing CLI contracts. Checks predictability, defense in depth, and context efficiency with evidence scores.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- ontology-of-everything/concept-skillsword for word, first seen Nov 15, 2026
Other versions1 project uses a version of this.
Word for word · 1
- ontology-of-everything/concept-skills★ 14100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository22 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- architect-4cSkill
- architect-4rSkill
- architect-frontend-feature-firstSkill
- architect-frontend-fsdSkill
- concept-designSkill
- concept-modelSkill
- data-knowledge-architectSkill
- personal-knowledge-architectSkill
- read-it-reframe-it-own-itSkill
- simplify-javaSkill
- agent-dx-cli-cnSkill
- architect-4c-cnSkill
- architect-4r-cnSkill
- architect-frontend-feature-first-cnSkill
- architect-frontend-fsd-cnSkill
- concept-design-cnSkill
- concept-model-cnSkill
- data-knowledge-architect-cnSkill
- personal-knowledge-architect-cnSkill
- read-it-reframe-it-own-it-cnSkill
- simplify-java-cnSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
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
- Distinctive: line 18
Read principles, reasons, and examples.
- Distinctive: line 20
Verify positive and negative cases in an authorized isolated fixture.
- Distinctive: line 32
Default to non-interactive execution.
- Distinctive: line 33
Treat agent input as untrusted.
- Distinctive: line 34
Treat server content as untrusted data even after sanitization.
≈ “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.
Files
Agent DX CLI
Design, review, and refactor CLIs for agents. Preserve the user's scope, stack, and existing authorization. Human conveniences and agent contracts can coexist; add only mechanisms the task needs.
Workflow
- Inspect code, current help/schema, and actual output. Record the CLI artifact and version.
- Read principles, reasons, and examples. Assess all applicable checks; distinguish missing, unverified, and verified behavior.
- Implement authorized changes, fixing acceptance blockers first. Reuse established libraries and share validation/execution across CLI, MCP, and batch surfaces.
- Verify positive and negative cases in an authorized isolated fixture. Report changes, per-check evidence, scores, and unresolved limits.
Proceed when facts and authorization suffice. Clarify only ambiguity that changes the target or consequences. A review request authorizes review only.
Principles
- Predictability: preserve typed intent from input to outcome; expose a queryable contract instead of requiring guesses.
- Defense in depth: validate input, enforce current permissions, and reconcile outcomes independently; one safeguard cannot replace another.
- Context efficiency: return bounded data and load task-relevant knowledge; every extra field or instruction must earn its cost.
Execution boundaries
- Default to non-interactive execution. Optional interaction requires explicit selection and a TTY.
- Treat agent input as untrusted. Enforce typed, field-specific constraints in the shared executor before business effects.
- Treat server content as untrusted data even after sanitization; preserve provenance.
- Destructive operations must provide
--dry-run. Declare the actual effects of previewing. - Schema, previews, quality reports, and confirmation flags do not grant permission. Recheck authorization at execution.
- Return
unknownfor unresolved outcomes. Reconcile before safe replay; report completion only after the requested result is verified.
Optional references
- For API/GWS alignment, use GWS practice. Retain its pinned version and verify project differences.
- For companion skill authoring or review, use SKILL+CLI authoring. Separate the four disclosure layers and retain useful decision guidance. Compare materially changed guidance with a no-skill baseline; stale syntax or misleading rules can make performance worse.
Scoring and acceptance
The patterns reference defines ten dimensions with two checks each. Score each check 0–5; the total is 100. This is the skill's scoring convention.
| Score | Required evidence |
| 0 | Missing or contradicted. |
| 1 | Documented only. |
| 2 | Implemented but unverified. |
| 3 | Positive cases passed. |
| 4 | Relevant negative cases passed. |
| 5 | End-to-end validation passed in the target environment. |
For static criteria: 3 means implementation review; 4 means consumer and negative-case comparison; 5 means reproducible contract or dependency checks. Attach evidence and the tested artifact/version to every score. Necessary behavior must be verified before acceptance. Acceptance requires at least 90 overall, with validation and authentication each at least 9. Credential leaks, authorization bypass, preview business writes, unsafe replay, or false completion block acceptance regardless of score. Explain every N/A; requested but missing features are not N/A. Report raw points and normalized score: raw points / applicable maximum × 100.
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
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.

