agentmods.dev

investigate-removed-item

investigate-removed-item is a skill for Codex from zja0011/edgesentinel-visionops. It costs 52 tokens per session (334 once invoked), scanned A, original, Apache-2.0.

A guided workflow for investigating events where an object was detected as removed. It checks event details and verifies whether the related evidence is intact.

In plain words
What is it for?
Checking when and where an object disappeared, what type it was, how the count changed, how the event was handled, and whether its evidence passed verification.
Why use it?
It separates what the recorded evidence proves from what it does not, such as identifying who caused the removal.

Skill for Codex

Written for Codex: agents/openai.yaml present.

not rated 21repo 2mo ago A scan 52 tokens original Apache-2.0

Good fit Checking when and where an object disappeared, what type it was, how the count changed, how the event was handled, and whether its evidence passed verification.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zja0011/edgesentinel-visionops/investigate-removed-item
View source ↗ zja0011/edgesentinel-visionops zja0011.github.io
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add zja0011/edgesentinel-visionops --skill investigate-removed-item
Clone the repo
git clone --depth 1 https://github.com/zja0011/edgesentinel-visionops

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for investigate-removed-item

README.md
[![agentmods](https://agentmods.dev/badge/skills/zja0011/edgesentinel-visionops/investigate-removed-item/github.svg)](https://agentmods.dev/skills/zja0011/edgesentinel-visionops/investigate-removed-item)
Your own site
<a href="https://agentmods.dev/skills/zja0011/edgesentinel-visionops/investigate-removed-item"><img src="https://agentmods.dev/badge/skills/zja0011/edgesentinel-visionops/investigate-removed-item/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for investigate-removed-item

Your own site · 80×15
<a href="https://agentmods.dev/skills/zja0011/edgesentinel-visionops/investigate-removed-item"><img src="https://agentmods.dev/badge/skills/zja0011/edgesentinel-visionops/investigate-removed-item.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 334 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.00334
Opus 5.5 $0.00021 $0.00134
Sonnet 5.5 $0.00010 $0.00067
Haiku 4.5 $0.00005 $0.00033

Measured 2mo ago against content hash 04a736054c39, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

investigate-removed-item scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/investigate-removed-item/SKILL.md · 29 lines

What it actually says

Investigate a removed item

Use this workflow when the user asks whether an object was removed, asks to investigate a removal, or asks who took an object.

  1. Call event.query with event_type=OBJECT_REMOVED, a bounded limit, and the exact detector object_class when the user states one.
  2. If an event is returned and more detail or evidence integrity is necessary, call event.get_detail and evidence.verify_event for the same most relevant exact event_id together in one model response. Do not spread these independent reads across separate model rounds.
  3. Report whether evidence is valid, but never claim that integrity verification identifies a person.
  4. Keep every conclusion tied to Tool results. A removal event proves a count change, not who caused it. If no identity evidence exists, explicitly say that the responsible person cannot be determined.
  5. Do not call tools outside required_tools. Do not acknowledge events, capture snapshots, restart the camera, generate files, or perform cleanup.

Answer in the user's language. Include event time, camera, zone, object class, count change, disposition, and evidence status only when those fields are available. State when data is stale, absent, incomplete, or outside the query window.

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 29 lines · 52 tokens per session scan A 04a736054c39

Subscribe to this mod's changes

investigate-removed-item is a skill published in the GitHub repository zja0011/edgesentinel-visionops (21 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 52 tokens to every session and 334 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

agent-harnessai-agentcomputer-visiondeepseekdisaster-recoverydocker
Related

investigate-removed-item compared with skills from other repositories

investigate-removed-item next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
investigate-removed-itemzja0011/edgesentinel-visionopsSkill212mo agoApache-2.0A52Codex
figma-useHaohao-end/openagentSkill748yesterdayMITA114Codex
cli-creatorHaohao-end/openagentSkill748yesterdayMITA82Codex
skillAnionex/dsh-vision-toolkitSkill92710d agoMITA0Claude Code, Codex
cloudflare-deployHaohao-end/openagentSkill748yesterdayMITA43Codex
vercel-deployHaohao-end/openagentSkill748yesterdayMITA47Codex
chatgpt-appsHaohao-end/openagentSkill748yesterdayMITA96Codex