agentleFS
XakkiXakki/ai-agents-skills/skills/security-access-diagnose/SKILL.md

security-access-diagnose

Skill6 starsChanged 3 months agoMITView on GitHub

Diagnose an access refusal while preserving native approval and security boundaries. Use when a task meets a filesystem, credential, provider or approval refusal. RU: отказ в доступе.

The file

Files
SKILL.md

Access-boundary diagnosis

Use when an authorized task encounters a filesystem, credential, provider or native approval refusal. Preserve the exact operation, target, native outcome and scope. Distinguish a pre-execution veto from an executed permission error, missing prerequisite, timeout or ordinary application failure; do not infer the reason from a generic error alone.

Stop the denied operation and do not bypass a security or approval veto by substituting another tool, identity, read route or weaker guard. A denied content read does not authorize obtaining that content through a search, hash, historical object or alternate controller. Continue independent authorized work only when the applicable stop scope permits it.

Reuse existing task and operation grants without asking for the same permission again; separately identify any genuinely missing resource access or native action approval. An unanswered approval is not consent. Record what ran, what did not run, partial effects and the narrow unresolved boundary. A fixture test or source inspection establishes only its observed scope, not restored admission to a protected live operation.

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.