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 merge-to-devgit 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/merge-to-dev)<a href="https://agentmods.dev/skills/nullhack/temple8/merge-to-dev"><img src="https://agentmods.dev/badge/skills/nullhack/temple8/merge-to-dev/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/merge-to-dev"><img src="https://agentmods.dev/badge/skills/nullhack/temple8/merge-to-dev.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 | $0.00031 | $0.00367 |
| Opus 5.5 | $0.00012 | $0.00147 |
| Sonnet 5.5 | $0.00006 | $0.00073 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
merge-to-dev 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
Merge To Dev
- Load [[software-craft/git-conventions]], [[software-craft/docstring-lifecycle]] — squash-merge form and the docstring lifecycle.
- Switch to dev and squash-merge the feature branch (
feature/<session_id>) per [[software-craft/git-conventions]]; the green-suite and whole-suite stubtest gate is verified on dev after the merge. Delete the merged branch (git branch -d feature/<session_id>) — no dangling branches. - Verify the full suite is green on dev after the merge: no pending markers remain (every source .pyi has its sibling .py, so every test runs) and every test passes.
- Verify whole-suite stubtest is clean across both source and tests: every source .pyi and every test .pyi agrees with its sibling .py — no drift smuggled in by the batch.
- Regenerate docstrings for the public surface of every contract shipped this cycle (modules, classes, public functions and methods) — faithful prose from the stable code, never a mechanical restatement of the signature; the why of an architectural decision lives in an ADR, not a docstring. Per [[software-craft/docstring-lifecycle]].
- Run
task lint-merge— addsSIMandRUFto the dev select and runsruff format .— so restructure and format land on dev exactly once per merge, never during build. - Commit the regenerated docstrings and the format pass on dev as
docs(<scope>): regenerate docstrings + format.
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 · 15 lines · 31 tokens per session scan A 0cb216fcb0d0
merge-to-dev is a skill published in the GitHub repository nullhack/temple8 (11 stars, last pushed 29d ago), licensed MIT. It adds 31 tokens to every session and 367 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
clawrium-release-announcements
Daily — draft a release blog post, open a PR, iterate on comments until merged.
blog-author
Watch ric03uec/clawrium release tags; draft a short blog post per user-visible feature as a PR against blog/.
release-watcher
Watch upstream Claw releases and clawrium discussions; surface top 3 feature candidates to Devashish via Discord DM for approve/skip.
build-prs-from-tickets
Implement a planned scope of GitHub or GitLab issues with agents - each ticket is implemented in its own worktree, reviewed, tested, and opened as its own PR or MR. Use when the user says "execute tickets", "implement the tickets for scope", "run the scope", or "build-prs-from-tickets ".
git-push-workflow
This skill should be used when the user says "push", "push to remote", "create PR", "create MR", "pull request", "merge request", "open PR", or when committing and pushing code to GitHub or GitLab. Covers git workflow rules, branch naming conventions, commit message format, and the push + PR/MR creation procedure.
commit_push
Format code, review changes, commit, and push to remote.