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 chakri192/ripple --skill incident-triagegit clone --depth 1 https://github.com/chakri192/rippleWrote 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/chakri192/ripple/incident-triage)<a href="https://agentmods.dev/skills/chakri192/ripple/incident-triage"><img src="https://agentmods.dev/badge/skills/chakri192/ripple/incident-triage/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/chakri192/ripple/incident-triage"><img src="https://agentmods.dev/badge/skills/chakri192/ripple/incident-triage.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 | $0.00096 | $0.01141 |
| Opus 5 | $0.00048 | $0.00571 |
| Sonnet 5 | $0.00019 | $0.00228 |
| Haiku 4.5 | $0.00010 | $0.00114 |
Grade A, and why
incident-triage 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 10d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Incident Triage Skill
A reusable DataHub Agent Skill that turns "this asset broke" into an actionable, persisted incident. It works with any MCP client connected to the DataHub MCP Server. Read-only tools do the investigation; mutation tools persist the result.
The split is deliberate: lineage traversal, owner resolution, and ranking are deterministic — same input, same output, every run. A model is only used to write the human-readable narrative. Nothing about what is affected is generated by a model, which is what makes the result safe to act on.
When to use
Trigger this skill when the user says any of:
- "X broke / is failing / has bad data — what's affected?"
- "What breaks if I change / drop / rename X?"
- "Who owns the things downstream of X?"
- "Open an incident for X."
Inputs
target— the URN (or a name to search for) of the broken / at-risk asset.
Procedure
-
Resolve the target. If given a name rather than a URN, call
searchto find the matching entity; confirm with the user if ambiguous. -
Trace the blast radius. Call
get_lineagewithdirection: DOWNSTREAMand a generous hop count. Collect every downstream dataset, dashboard, chart, and model, keeping each entity's hop distance (degree) from the source. -
Enrich. For the affected entities, call
get_entitiesto pull ownership, platform, domains, and glossary terms. Flag customer-facing surfaces (dashboards / charts) and owned production tables as high priority. -
Rank. Order the blast radius by criticality: customer-facing first, then owned production assets, then everything else, with closer hops ranked higher. A simple, transparent scoring function keeps the ranking reproducible.
-
Report. Produce a concise Markdown incident report:
- a one-line summary of scope (N assets, M customer-facing, owners to page),
- a ranked impact table (asset · platform · type · hops · owners),
- a short recommended-actions checklist.
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.
- 10d ago First seen · 104 lines · 96 tokens per session scan A 12368ea628b1
incident-triage is a skill published in the GitHub repository chakri192/ripple (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 96 tokens to every session and 1,141 once invoked, about $0.0005 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
zarr-python
Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.
claw-admin
Claw system administration: service management, IM connections, logs, cron, and workspace diagnostics. Use when the user asks to manage claw services, connect/disconnect IM platforms, view logs, or perform system-wide operations.
session-investigator
Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool…
aeon
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard…
optimize
Review code for efficiency and performance. Triggered by "/optimize" when user wants to identify bottlenecks or improve performance.
geopandas
Python library for working with geospatial vector data including shapefiles, GeoJSON, and GeoPackage files. Use when working with geographic data for spatial analysis, geometric operations, coordinate transformations, spatial joins, overlay operations, choropleth mapping, or any task involving…