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 Giskard-AI/giskard-skills --skill giskard-to-collibragit clone --depth 1 https://github.com/Giskard-AI/giskard-skillsWrote 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/giskard-ai/giskard-skills/giskard-to-collibra)<a href="https://agentmods.dev/skills/giskard-ai/giskard-skills/giskard-to-collibra"><img src="https://agentmods.dev/badge/skills/giskard-ai/giskard-skills/giskard-to-collibra/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/giskard-ai/giskard-skills/giskard-to-collibra"><img src="https://agentmods.dev/badge/skills/giskard-ai/giskard-skills/giskard-to-collibra.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 | $0.00116 | $0.00804 |
| Opus 5 | $0.00058 | $0.00402 |
| Sonnet 5 | $0.00023 | $0.00161 |
| Haiku 4.5 | $0.00012 | $0.00080 |
Grade A, and why
giskard-to-collibra 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 12d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Giskard to Collibra export
This skill is self-contained. scripts/giskard_to_collibra.py does the whole job: it finds the scan in Giskard Hub, builds the Collibra asset hierarchy (AI Agent, AI Agent Version, AI Endpoint, AI Monitors, and the deployment complex relation), imports it into Collibra, and pushes pass/fail metrics.
All paths below are relative to this skill's base directory.
One-time setup
The user may not be technical. Do these checks for them and explain in plain language.
- Check Python 3.10 or newer is available (
python3 --version). - Install the dependencies:
python3 -m pip install -r requirements.txt. If the environment blocks system-wide installs, create a virtualenv first and use its Python for every command below. - Check that a
.envfile exists in the current working directory (or next to the script) with values for all six variables listed inenv.example. If the file is missing, or any of the six variables has no value, do not guess and do not proceed. Explicitly ask the user for each missing value, then create or complete.env. Never print or echo the secret values back.
Run the export
- If the user gives a scan ID, run
python3 scripts/giskard_to_collibra.py --scan-id <SCAN_ID>. It exports exactly that scan. Done. - If the user gives a project ID, run
python3 scripts/giskard_to_collibra.py --project-id <PROJECT_ID>. It exports the project's latest finished scan. Done. - If the user gives a project name (the usual case), first run
python3 scripts/giskard_to_collibra.py --list-projects. It prints oneid nameline per project. Match the user's words against the names yourself. Tolerate case differences and small typos ("zyphyr" means "Zephyr"). If the match is not obvious, show the names and ask the user. Then run with--project-id <the matched id>.
The script loads .env itself, waits for the Collibra import job, and prints a link to the agent asset in Collibra. Share that link with the user.
Notes
What ships with it
3 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.
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.
- 12d ago First seen · 40 lines · 116 tokens per session scan A cd50b66dcd37
giskard-to-collibra is a skill published in the GitHub repository Giskard-AI/giskard-skills (5 stars, last pushed 15d ago), licensed Apache-2.0. It adds 116 tokens to every session and 804 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
reporting-adverse-events
Structures adverse-event mentions that OpenMed extracts into FAERS / ICH E2B(R3) reportable fields — suspect drug, reaction (MedDRA PT), seriousness criteria, and outcome. Use when the user needs to build an individual case safety report (ICSR), populate a FAERS submission, map a narrative to E2B(R3) data elements…
auditing-deidentification-runs
Produce a signed, reproducible, no-PHI audit trail for an OpenMed de-identification run via deidentify(audit=True). Use when the user needs compliance evidence, a tamper-evident record of what was redacted and why, to verify nothing was changed, to retain proof for HIPAA/GDPR audits, or to review de-id decisions…
pseudonymizing-for-gdpr
Apply GDPR-grade pseudonymization to clinical or personal text with OpenMed, keeping a separately-held re-linkage key so the data can be controlled-re-linked later. Use when the user must process EU personal/health data under GDPR, asks for pseudonymization vs anonymization, needs Art. 4(5) / Art. 9 / Recital 26…
validating-us-core
Validate FHIR R4 resources and Bundles against US Core / USCDI profiles with the official HL7 FHIR validator before submitting to an EHR. Covers running validatorcli.jar (or the public validator.fhir.org), declaring meta.profile, must-support elements, common conformance gaps (missing code/category/status), and…
fda-database
Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.
setup-openmed
Collect a bounded set of de-identification policy decisions and write a deterministic, reviewable DEID-POLICY.md from the versioned local template. Use when a project needs explicit jurisdiction, recall floor, surrogate strategy, model policy, audit location, and human approval before privacy work begins.