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.
npx skills add Borda/vision-delivery --skill check-sentinel-setupgit clone --depth 1 https://github.com/Borda/vision-deliveryWrote 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.
[](https://agentmods.dev/skills/borda/vision-delivery/check-sentinel-setup)<a href="https://agentmods.dev/skills/borda/vision-delivery/check-sentinel-setup"><img src="https://agentmods.dev/badge/skills/borda/vision-delivery/check-sentinel-setup.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00127 | $0.00486 |
| Opus 5 | $0.00063 | $0.00243 |
| Sonnet 5 | $0.00025 | $0.00097 |
| Haiku 4.5 | $0.00013 | $0.00049 |
Grade A, and why
check-sentinel-setup 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 8d 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.
What it actually says
Check Sentinel Setup
Diagnose setup in layers without guessing host state or copying upstream Roboflow authentication recipes.
Run the offline package check
Resolve the plugin root from this loaded skill file, then run from any working directory:
python <plugin-root>/resources/scripts/sentinel_doctor.py --json
Do not assume the current project is the plugin checkout. The doctor checks synchronized manifests, the URL-only MCP entry, packaged resources, and discoverable skills. It performs no network or account operation.
If the doctor fails, report every failed check and recommend reinstalling with the two host-specific commands in the repository quick start. Do not edit host settings automatically.
Check the host layer
After the offline status is passed:
- Verify
sentinel@sentinelis installed and enabled using host-visible plugin state when available. - Verify the host exposes the bundled skills and a
roboflowMCP server configured at the expected URL. Never infer this from repository files alone. - Report Roboflow authorization as
unverifiedunless an authenticated read actually succeeds in the active host. - When connection recovery is needed, load sibling
../auth-setup/SKILL.mdand follow it. Do not restate a provider credential, API, or UI recipe here.
Report
Return three separate results:
package:passed|failed, with doctor evidence;host:passed|failed|unverified, with installed/enabled evidence;roboflow_auth:passed|failed|unverified, only from an observed host result.
Never collapse a healthy package into “fully working” while the host or authenticated service remains unverified.
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.
- 8d ago First seen · 41 lines · 127 tokens per session scan A 018d22c421c7
check-sentinel-setup is a skill published in the GitHub repository Borda/vision-delivery (4 stars, last pushed 28d ago), licensed Apache-2.0. It adds 127 tokens to every session and 486 once invoked, about $0.0006 per session on Opus 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 2026-08-31.
Other skills, from other repositories
bug-fix
Use when a bug, regression, or unexpected behaviour is reported and the user wants it fixed end to end — "why is X broken", "this stopped working after Y", "fix this crash". Also use when a symptom is known but its cause is not. Not for building new behaviour, and not for a change whose cause is already proven.
bug-investigate
Use when someone wants to know WHY something is broken and has not asked for it to be fixed — "why is this happening", "what's causing this error", "find out what's wrong", "diagnose this before we decide". Also use before committing to a fix, when the cause is unknown and the decision depends on it. Not for fixing …
pw-doctor
Diagnose the Prewalk installation, presets, hook manifest, state directory, and Claude Task routing setup.
postmortem
Auto-generates a structured postmortem from a completed campaign. Reads the campaign file, telemetry logs, and feature ledger. Produces a documented analysis of what broke, what the safety systems caught, and what patterns emerged. Can also be invoked manually for any incident.
systematic-debugging
4-phase root cause analysis: observe, hypothesize, verify, fix. Enforces investigation before any code changes. Emergency stop after 2 failed fixes. Prevents shotgun debugging and fix cascades.
zapier-status
Check the health of your Zapier MCP setup. Three modes — health check (dashboard view), audit (find waste and duplicates), diagnose (systematic troubleshooting). Use when asking "is my MCP working?", "check my tools", "audit my setup", "what's broken?", or "zapier status".