Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/FoloToy/ai-passportnpx agentmods add skills/folotoy/ai-passport/passport-buildWrote 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/folotoy/ai-passport/passport-build)<a href="https://agentmods.dev/skills/folotoy/ai-passport/passport-build"><img src="https://agentmods.dev/badge/skills/folotoy/ai-passport/passport-build/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.
<a href="https://agentmods.dev/skills/folotoy/ai-passport/passport-build"><img src="https://agentmods.dev/badge/skills/folotoy/ai-passport/passport-build.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00043 | $0.00765 |
| Opus 5.5 | $0.00017 | $0.00306 |
| Sonnet 5.5 | $0.00009 | $0.00153 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
passport-build 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build and Package Firmware
Resolve the target checkout, run git status --short --branch, and read
AGENTS.md, docs/development/engineering/build-and-test.md, and
docs/development/engineering/firmware-layout.md there. All commands below run
from that checkout; never infer a developer-specific IDF path.
Build the requested configuration
- Confirm ESP-IDF 5.5.3 is activated. If missing, use
passport-setupwhen available or its environment-setup document. Obtain required network/system permissions rather than bypassing them. - Check tracked defaults, dependencies, and partitions against the requested
application. The gate uses isolated configuration from
sdkconfig.defaults, not the ignored rootsdkconfig. If the user wants a local-only setting in the delivered firmware, resolve that mismatch explicitly; do not silently overwrite configuration or build a different variant. - Run the smallest relevant checks while iterating and
./tools/validate.shbefore final delivery. This is the existing gate, not a replacement build pipeline. Custom valid partition layouts are allowed. On a requested build-only check,./tools/validate.sh --firmwareis available; identify any omitted host tests in the report. - A failed run does not validate an old file still present under
build/. Correct in-scope failures or report the blocker. Never deliver a stale artifact as the result of the failed build.
Identify the exact deliverable
The gate preserves build/FoloToy-AI-Passport-full.bin and a content-addressed
bundle under build/firmware/<full-bin-sha256>/. Verify the bundle before
handoff with:
python3 tools/archive_firmware.py verify <archive-directory>
Report the actual archive path, full-image hash, and matching ELF identity from
manifest.json. The archive retains ELF, MAP, merged, application, bootloader,
and partition-table images, and flash_args. Extra custom partition images are
not retained separately; obtain them if needed for segmented flashing. A repeat
archive of identical firmware reuses its first verified MAP as documented in the
build guide. Do not substitute an ELF from a later rebuild,
especially for a dirty checkout. The recorded hashes bind artifacts together;
they are not a claim of hardware acceptance or cryptographic trust in a vendor.
What ships with it
1 file 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.
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.
- 1mo ago First seen · 69 lines · 43 tokens per session scan A 58663d26d30f
passport-build is a skill published in the GitHub repository FoloToy/ai-passport (646 stars, last pushed 2d ago), licensed MIT. It adds 43 tokens to every session and 765 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 2026-09-17.
Other skills, from other repositories
jetson-video-pipeline
Use when planning, executing, and independently validating Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decode, AV1, or concise acceptance workflows.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
SmartHome Video Anomaly Benchmark
VLM evaluation suite for video anomaly detection in smart home camera footage.
holohub-app-lifecycle
Use for non-failing HoloHub app work with ./holohub: scaffold, build, run, test, visual evidence, lint, and flow benchmarking.
ros2-robotics
Best practices for ROS 2 robotics development, covering package structure, nodes, topics/services/actions, launch files, QoS, tf2 transforms, and testing. Use when creating ROS 2 packages, writing nodes in rclpy or rclcpp, defining custom messages/services/actions, writing launch files, configuring QoS profiles…
tia-testsuite
TIA Portal V21 Test Suite operations. Use for Application Tests with PLCSIM, Style Guide rules, System Tests through OPC UA, import/scope management, execution, and recursive result evaluation.