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 first-tree-ai/first-tree --skill first-tree-qagit clone --depth 1 https://github.com/first-tree-ai/first-treeWrote 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/first-tree-ai/first-tree/first-tree-qa)<a href="https://agentmods.dev/skills/first-tree-ai/first-tree/first-tree-qa"><img src="https://agentmods.dev/badge/skills/first-tree-ai/first-tree/first-tree-qa/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/first-tree-ai/first-tree/first-tree-qa"><img src="https://agentmods.dev/badge/skills/first-tree-ai/first-tree/first-tree-qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00078 | $0.01613 |
| Opus 5.5 | $0.00031 | $0.00645 |
| Sonnet 5.5 | $0.00016 | $0.00323 |
| Haiku 4.5 | $0.00008 | $0.00161 |
Grade A, and why
first-tree-qa 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
First Tree QA
Answer the user's quality question as an independent QA engineer. Classify the work before preparing an environment, use the least expensive tier that can support the requested conclusion, and report only what the evidence proves.
Principles
- Do not change product source while testing it. Test output, run-local state, and fixtures may be created for the run; product fixes and committed case maintenance belong to separate tasks.
- Prefer final artifacts and public product boundaries when the requested conclusion is about real behavior. Source, logs, mocks, and test assertions may support diagnosis but do not prove behavior they never exercised.
- Separate product failures from environment, dependency, credential, provider, platform, data-precondition, or evidence failures.
- Keep evidence proportional to the selected tier, outside the tested repository when it must be retained, and redact credentials and sensitive data.
- Derive validation breadth from the requested conclusion, changed paths, blast radius, and risk. Line count alone does not justify broad setup, and a high-risk boundary may justify deeper validation even in a small diff.
- Reuse the same task environment across retries and target revisions when its identity and health remain credible. Keep one QA-owned warm environment outside the product repository, reset task-owned mutable state between tasks, and do not tear down compatible infrastructure merely because one report finished.
- Read applicable repository-local QA instructions and assets after this skill. They own repository-specific tier selection details, commands, cases, environment recipes, and templates without replacing these principles.
Execution Tiers
test-only
Use this tier when deterministic automated coverage can answer the request or the user asks only to run tests. Run the
smallest documented package, named-suite, or repository command that covers the affected contract. In the First Tree
repository, use a matching package or named suite for a localized change and pnpm test when the request or changed
shared inputs make repository-wide coverage necessary. Record the exact target, command, exit result, and material
failures.
What ships with it
2 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.
- 1mo ago First seen · 120 lines · 78 tokens per session scan A a83bc30fdd86
first-tree-qa is a skill published in the GitHub repository first-tree-ai/first-tree (157 stars, last pushed 8d ago), licensed Apache-2.0. It adds 78 tokens to every session and 1,613 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
llm-as-judge-evaluation
Evaluate LLM outputs using frontier models as judges. Use for pairwise model comparison, quality scoring with custom rubrics, and automated evaluation pipelines. Covers position bias mitigation, statistical significance, and generating preference data for DPO/RLHF.
skillshare-implement-feature
Implement a feature from a spec file or description using TDD workflow. Use this skill whenever the user asks to: add a new CLI command, implement a feature from a spec, build new functionality, add a flag, create a new internal package, or write Go code for skillshare. This skill enforces test-first development…
dd-triage-flaky-test
Load when investigating a specific flaky test. Gets history, failure pattern, and category, then recommends fix, quarantine, or escalate.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.