Apache Doris Skills is a collection of agent instructions containing Apache Doris database knowledge for designing, sizing, operating, diagnosing, and contributing to Doris clusters. It serves developers and operators using Claude Code, Cursor, Codex, Cline, Amp, and other agent tools, with the skills providing decision logic and evidence-based workflows.
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 apache/doris-skills --skill develop-with-evidencegit clone --depth 1 https://github.com/apache/doris-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/apache/doris-skills/develop-with-evidence)<a href="https://agentmods.dev/skills/apache/doris-skills/develop-with-evidence"><img src="https://agentmods.dev/badge/skills/apache/doris-skills/develop-with-evidence/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/apache/doris-skills/develop-with-evidence"><img src="https://agentmods.dev/badge/skills/apache/doris-skills/develop-with-evidence.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 | $0.00147 | $0.01057 |
| Opus 5.5 | $0.00059 | $0.00423 |
| Sonnet 5.5 | $0.00029 | $0.00211 |
| Haiku 4.5 | $0.00015 | $0.00106 |
Grade A, and why
develop-with-evidence 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developing with evidence
Make the goal, the implementation, the verification, and the final description of a change agree with one another. Build evidence around actual behavior, and verify in proportion: each check should settle a specific uncertainty.
Boundaries
- Use this skill from the moment you start to understand the task until the local implementation, verification, self-review, and delivery notes are done. When you take over an existing patch, fill in the key evidence it lacks.
- The main agent makes every judgment, every code change, and the final conclusions. When the environment offers subagents, evidence gathering that reads a lot and comes back with checkable conclusions can go to them, to keep the main session's context small; see subagents.md. Don't run a cross-model review or bring in external reviewers on this skill's account, and call the self-review at each stage what it is: a self-review.
- Publishing the PR, following CI and answering reviews after it is published, watching the change after it merges, and recurring tasks are outside this skill. At delivery, write the handoff file, with a PR description draft and the facts behind it, for the PR step to use; it is no trigger to publish, merge, or deploy anything automatically.
- Follow the user's requests, the project's conventions, and the authorizations already given. When the scope is clear, keep going; don't add approvals for routine steps. Ask a specific question only when a behavioral contract, a compatibility question, or an irreversible trade-off truly cannot be settled from the information at hand, and first finish the work that can proceed without the answer.
- When fixing a bug, confirm that the defect is real before changing code, as stage 1 describes. When the defect is proven not to exist, or it can neither be reproduced nor traced through a causal chain, stop developing, explain the evidence, and ask the developer how to proceed. This holds even when you find out in a later stage.
- Keep the developer's existing changes: don't reset the working tree, don't slip in unrelated cleanup, and don't run unauthorized migrations on real data. Don't widen the change just to gather evidence.
What ships with it
22 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.
- agents/openai.yaml 1.3 KB
- assets/icon.svg 1.7 KB
- references/change-types/bugfix.md 1.6 KB
- references/change-types/config-build-migration.md 1.1 KB
- references/change-types/enhancement.md 624 B
- references/change-types/feature.md 806 B
- references/change-types/frontend-and-low-impact.md 578 B
- references/change-types/index.md 3.4 KB
- references/change-types/performance.md 1.4 KB
- references/change-types/refactor.md 969 B
- references/change-types/revert.md 302 B
- references/change-types/test-ci.md 1.1 KB
- references/evidence-entry.md 2.9 KB
- references/handoff.md 5.4 KB
- references/sources.md 713 B
- references/stages/1-scope.md 5.9 KB
- references/stages/2-implement.md 2.2 KB
- references/stages/3-verify.md 3.7 KB
- references/stages/4-self-review.md 1.6 KB
- references/stages/5-evidence.md 2.2 KB
- references/stages/6-deliver.md 3.1 KB
- references/subagents.md 3.3 KB
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 · 35 lines · 0 tokens per session scan A ce7fafd68422
develop-with-evidence is a skill published in the GitHub repository apache/doris-skills (49 stars, last pushed 2d ago), licensed Apache-2.0. It adds 147 tokens to every session and 1,057 once invoked, about $0.0006 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 2026-11-05.
develop-with-evidence compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| develop-with-evidenceapache/doris-skills | Skill | 49 | 2d ago | Apache-2.0 | A | 147 | Codex |
| cf-review-indinhanhthi/coding-friend | Skill | 4 | today | MIT | A | 50 | Claude Code |
| cf-review-outdinhanhthi/coding-friend | Skill | 4 | today | MIT | A | 60 | Claude Code |
| cf-tdddinhanhthi/coding-friend | Skill | 4 | today | MIT | A | 140 | Claude Code |
| cf-review-customdinhanhthi/coding-friend | Skill | 4 | today | MIT | A | 0 | Claude Code, Codex |
| cf-verificationdinhanhthi/coding-friend | Skill | 4 | today | MIT | A | 122 | Claude Code |
| cf-plan-reviewdinhanhthi/coding-friend | Skill | 4 | today | MIT | B | 90 | Claude Code |