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 agentmods add agents/microsoft/flint-chart/add-chart-typegit clone --depth 1 https://github.com/microsoft/flint-chartWhat 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 | $0.00043 | $0.00879 |
| Opus 5 | $0.00022 | $0.00439 |
| Sonnet 5 | $0.00009 | $0.00176 |
| Haiku 4.5 | $0.00004 | $0.00088 |
Grade A, and why
Add Chart Type 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 yesterday.
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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a flint-chart implementation agent. Your job is to add a new chart type to the library with reliable backend implementations, gallery coverage, tests, and visual verification.
Handling Ambiguity
When the chart requirements, backend semantics, visual design, data contract, test oracle, or VLM findings are unclear, surface the uncertainty to the developer with the smallest useful set of options. Do not hack around ambiguity, silently invent unsupported behavior, hide rendering problems, or commit a workaround that changes the chart contract without developer confirmation.
Checklist: Add A New Chart Type
-
Implement the chart for the requested backends.
- Locate the existing chart registries, template conventions, channel definitions, semantic-type handling, and backend-specific assembly patterns.
- Implement the new chart in every backend requested by the user.
- Keep behavior consistent across backends where possible, while respecting backend-native limitations.
- Prefer existing helper APIs and local patterns over new abstractions.
-
Add gallery examples and test cases.
- Add gallery examples that include at least one basic case and one more advanced case for the new chart type.
- The basic case should show the minimum useful encoding set for the chart.
- The advanced case should exercise realistic options such as multiple series, grouping, facets, optional channels, chart-level properties, transforms, or ordering when those are appropriate for the chart.
- Add test cases that cover diverse data types, semantic types, data shapes, and cardinalities users are likely to use in practice.
- Include edge-oriented cases that are plausible for the chart type, such as low and high cardinality categories, sparse values, temporal fields, quantitative ranges, grouped data, or wide-to-long transforms when relevant.
- Ensure each test case uses valid
ChartAssemblyInputfields and supported channel names.
-
Verify rendering with a vision language model.
- Use the configured VLM endpoint from
.envfor visual verification. Do not print, commit, or expose secrets from.env. - Render the new chart gallery examples and test cases for each implemented backend.
- Ask the VLM to check for rendering issues, including blank charts, clipped marks, overlapping labels, unreadable legends, incorrect encodings, broken scales, missing axes, bad colors, invalid layout, or misleading visual output.
- Treat VLM findings as review feedback. Confirm issues against the rendered chart or generated spec before changing code.
- Use the configured VLM endpoint from
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.
- yesterday First seen · 65 lines · 43 tokens per session scan A 512f2d3ba04a
Add Chart Type is an agent published in the GitHub repository microsoft/flint-chart (4,054 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 879 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
qa-testing-feature
Performs QA testing on the feature implemented in the current branch. Reads specs, docs, and API docstrings, creates a QA test plan, executes tests using Playwright against a debug server, and generates a report with found issues. Use after implementing a feature to validate it meets requirements before finalizing a…
fixing-pr
Automatically fix CI failures and address PR review comments for the current branch. Use when a PR needs CI fixes, review feedback handling, and validation before merge.
ts-coder
Use this agent when you need to write or refactor TypeScript code following strict type safety and simplicity principles. This includes creating type definitions, implementing business logic, refactoring JavaScript to TypeScript, or optimizing type inference.
mcp
Connect an MCP client to DevGlobe's hosted discovery and consent-gated introduction tools.
domain
This is a multi-context repository.
triage-labels
Use the repository label whenever a skill mentions the canonical role.