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 commands/altimateai/altimate-code/test-discoverygit clone --depth 1 https://github.com/AltimateAI/altimate-codeWhat 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 | $0.00030 | $0.02655 |
| Opus 5 | $0.00015 | $0.01327 |
| Sonnet 5 | $0.00006 | $0.00531 |
| Haiku 4.5 | $0.00003 | $0.00265 |
Grade A, and why
test-discovery 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 2d 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Discovery & Generation
You are a test engineer for altimate-code, a data engineering AI agent built as a fork of OpenCode. Your job is to find missing tests that would catch real bugs — not write tests for the sake of coverage.
Phase 1: Reconnaissance (15 min)
1.1 Understand what changed recently
# Recent commits (last 7 days)
git log --oneline --since="7 days ago" --no-merges | head -20
# Files changed recently
git diff HEAD~10..HEAD --stat | tail -20
# Any recent CI failures
gh run list --repo AltimateAI/altimate-code --limit 10 --json conclusion,name,headBranch --jq '.[] | select(.conclusion == "failure") | "\(.name): \(.headBranch)"'
1.2 Find untested code paths
# Files with no corresponding test
for f in $(find packages/opencode/src -name "*.ts" -not -path "*/tui/*" | head -40); do
base=$(basename "$f" .ts)
dir=$(basename $(dirname "$f"))
if ! find packages/opencode/test -name "${base}*test*" 2>/dev/null | grep -q .; then
echo "UNTESTED: $f"
fi
done
# Functions exported but never tested
grep -rn "export function\|export async function\|export const.*=" packages/opencode/src/cli/cmd/skill-helpers.ts packages/opencode/src/skill/skill.ts | head -20
1.3 Read the docs to understand user-facing features
Read these files to understand what users expect to work:
docs/docs/configure/skills.mddocs/docs/configure/tools/custom.mddocs/docs/configure/warehouses.mddocs/docs/configure/mcp-servers.mddocs/docs/data-engineering/tools/index.md
1.4 Research real-world usage
Search online for how people actually use altimate-code and similar tools:
- Search: "altimate-code" OR "altimate code" site:github.com
- Search: "opencode skills" OR "opencode plugin" issues bugs
- Search: "claude code skills" edge cases problems
- Search: "dbt agent" OR "data engineering AI agent" common failures
Look for:
- Bug reports or issues that reveal untested paths
- Usage patterns we haven't considered
- Edge cases from real projects (monorepos, CI/CD, Docker, Windows WSL)
- Integration scenarios (dbt + warehouse + skills together)
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.
- 2d ago First seen · 278 lines · 30 tokens per session scan A 77633e2e906a
test-discovery is a command published in the GitHub repository AltimateAI/altimate-code (803 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 2,655 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 commands, from other repositories
MIGRATE_DESIGN
Design doc for the migration tool PR. Author: Sol ([email protected]). Co-authored-by: wakesync.
awesome-chatgpt
Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.
agentlas-cloud
Staff a task only from the signed-in owner's Agent Cloud agents.
review-epo-claims
Analyze patent claims for EPO Art. 84 EPC compliance - clarity, conciseness, support by description.
commit
智能生成 Git 提交信息并提交.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.