AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified CC0-1.0 Self-run

Blindness Deafness

skill-hmbown-wizards-of-the-ghosts-blindness-deafness · by Hmbown

In D&D, Blindness/Deafness selectively removes one sense — the target can still act but loses critical awareness. The real-world version is selective channel muting: blocking a process from seeing certain inputs (input filtering, API response redaction), deafening it to specific signals (suppressing webhooks, ignoring certain event streams), or cutting telemetry so a system operates without aware…

No reviews yet
0 installs
19 views
0.0% view→install

Install

$ agentstack add skill-hmbown-wizards-of-the-ghosts-blindness-deafness

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-hmbown-wizards-of-the-ghosts-blindness-deafness)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
5mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Blindness Deafness? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Blindness/Deafness

Cut a system's eyes or ears — let it run, but blind to specific inputs or deaf to specific signals.

What This Skill Does

In D&D, Blindness/Deafness selectively removes one sense — the target can still act but loses critical awareness. The real-world version is selective channel muting: blocking a process from seeing certain inputs (input filtering, API response redaction), deafening it to specific signals (suppressing webhooks, ignoring certain event streams), or cutting telemetry so a system operates without awareness of a specific data source. Unlike containment (forcecage) which restricts everything, Blindness/Deafness surgically removes one information channel while leaving the rest intact. In this grimoire, Blindness/Deafness is treated as a literal spell with a shipping-now delivery profile. Canonical reference input: Blindness/Deafness (spell).

When To Use

  • A process should keep running, but one input, signal, or telemetry source needs to be removed from its awareness.
  • You need to suppress a specific webhook, event stream, API field, or sensor channel without containing the whole system.
  • You want to test or control behavior under selective sensory loss rather than full isolation.

Prerequisites

  • No extra runtime dependencies beyond Hermes Agent and the normal toolset for this session.

Procedure

  1. Restate the target, the success condition, and any no-touch boundaries before taking action.
  2. Identify the exact channel to mute and the decisions the system currently makes from it.
  3. Verify the channel is not safety-critical or load-bearing for core correctness.
  4. Choose the muting mechanism: input filtering, response redaction, event suppression, or telemetry cutoff.
  5. Define restoration triggers, operators, and monitoring so everyone knows the system is partially blind or deaf.
  6. Return the channel-muting plan with expected behavioral changes and rollback steps.
  7. Stop for explicit confirmation before taking a live action that changes access, triggers an alert, or touches a real system boundary.
  8. Package the result as the deliverables below, with confidence, assumptions, and unresolved risk called out explicitly.

Deliverables

  • A selective channel-muting plan naming exactly what input, signal, or telemetry was removed.
  • A dependency note explaining what decisions will proceed without that awareness channel.
  • Restoration triggers, rollback steps, and operator-facing documentation.

Pitfalls / Guardrails

  • Treat the live action surface as real operational work, not decorative lore.
  • Muting a channel the system needs for safety decisions is dangerous. Verify the blinded input is not load-bearing before cutting it.
  • Always document what was muted and set a restoration trigger. A system that forgets it is blind will make confident wrong decisions.

Verification

  • Check that the result includes every deliverable promised above.
  • Check that confirmed facts, assumptions, and inferences are visibly separated.
  • Check that the exact live target, confirmation gate, and rollback or recovery path are explicit.

Example Invocation

/blindness-deafness selectively blind or deafen this system to one input, signal, or telemetry source while keeping the rest of it running safely

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.