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 nullhack/temple8 --skill implement-from-stubgit clone --depth 1 https://github.com/nullhack/temple8Wrote 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/nullhack/temple8/implement-from-stub)<a href="https://agentmods.dev/skills/nullhack/temple8/implement-from-stub"><img src="https://agentmods.dev/badge/skills/nullhack/temple8/implement-from-stub/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/nullhack/temple8/implement-from-stub"><img src="https://agentmods.dev/badge/skills/nullhack/temple8/implement-from-stub.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 | $0.00029 | $0.00460 |
| Opus 5.5 | $0.00012 | $0.00184 |
| Sonnet 5.5 | $0.00006 | $0.00092 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
implement-from-stub 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.
What it actually says
Implement From Stub
- Load [[software-craft/source-stubs]], [[software-craft/tdd]], [[software-craft/design-patterns]] — stub sync, the cycle, and implementation patterns.
- Implement — or, for rework, re-implement — the .py from its .pyi. The .pyi signature is the spec; fill or correct the body to satisfy it and pass the tests. Keep the .py consistent with its sibling .pyi.
- Emit the structural artifacts the module requires, keyed on what it is: IF an ORM model THEN emit an Alembic migration (the migration is the schema spec); IF an external adapter THEN reproduce the recorded request shape exactly (method, path, query parameters, headers from external-contracts.md) — vcr matches the request strictly, so the implementation conforms to the cassette, not the other way around. Config follows 12-factor per [[software-craft/secrets-and-config]]: non-secret config via
load_dotenv()from the workspace.env; secrets viadotenv_values()from~/.secrets/<project>.env— read once into a frozen typed Settings, never intoos.environ. IF an auth-dependent test fails on credentials THEN stop and ask the user with suggestions — do not investigate the secret. - IF the body cannot satisfy the .pyi without changing it THEN that is a contract gap — do not edit the stub; escalate at review.
- Run stubtest scoped to the modules built this cycle — the source module(s) and the test module(s) whose pending marks were removed. The whole-suite stubtest waits until every source .py exists, because unbuilt sibling stubs would false-fail per [[software-craft/source-stubs]], [[software-craft/tdd]].
- Stubtest imports the runtime module, so every transitive runtime dependency must be installed in the project venv. IF an import is used only for types THEN prefer
if typing.TYPE_CHECKING:so stubtest does not pull heavy runtime deps for type-only references.
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 · 14 lines · 29 tokens per session scan A 7aa65238d79d
implement-from-stub is a skill published in the GitHub repository nullhack/temple8 (11 stars, last pushed 29d ago), licensed MIT. It adds 29 tokens to every session and 460 once invoked, about $0.0001 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
agentic-test-audit
Audit a pytest suite: surviving mutants and untested code, flaky, order-dependent and slow tests, and removal candidates checked on held-out mutants. Report-only.
agentic-verify
Check that a Python change is caught by tests: run every mutant of the changed lines and write tests until they catch them. Reports evidence instead of a diff to read.
test-generator
Generate pytest test cases for Python functions and classes.
python
Use when the task is Python itself, in any framework or none: PEP 695 generics, mypy --strict typing, dataclass/Protocol/TypedDict/Enum choices, asyncio.TaskGroup, stdlib idioms, src/ layout + pyproject.toml with uv, ruff+mypy+pytest gate. NOT a FastAPI/ASGI service (that is fastapi), NOT a deep pytest suite (that is…
tdd
Drive a red → green → refactor cycle for the active task.
uv-workflow
Use when a coding agent needs to run Python code, modules, one-liners, tools, tests, or standalone scripts through uv, or create and maintain PEP 723 scripts with uv init/add/remove --script. Avoid direct python/python3 shell entrypoints.