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 skills/zfinix/aster/refactor-safelynpx skills add Zfinix/aster --skill refactor-safelygit clone --depth 1 https://github.com/Zfinix/asterWhat 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 | $0.00044 | $0.00324 |
| Opus 5 | $0.00022 | $0.00162 |
| Sonnet 5 | $0.00009 | $0.00065 |
| Haiku 4.5 | $0.00004 | $0.00032 |
Grade A, and why
refactor-safely 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.
What it actually says
Refactor safely
- Map the blast radius first. Search every reference before changing one: the definition, call sites, tests, docs, config strings, serialization. A rename that misses a string reference compiles and then breaks at runtime.
- Green between every step. Refactor in compilable increments: move, check, rename, check. A ten-step refactor with one check at the end turns one mistake into an hour of archaeology.
- Never mix behavior change into a refactor. If you spot a bug mid refactor, note it, finish the neutral change, then fix the bug as its own change. Mixed diffs are unreviewable and unbisectable.
- Let the compiler drive mechanical renames. Change the definition first, then fix every error it reports; the error list is your checklist.
- Match the destination's conventions. Moved code adopts the naming, error handling, and comment density of the file it lands in.
- Prove neutrality at the end. The same tests that passed before must pass after, with no test edits beyond imports and paths. Any test that had to change semantically means it was not a refactor.
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 · 25 lines · 44 tokens per session scan A 1a5c5ac38461
refactor-safely is a skill published in the GitHub repository Zfinix/aster (40 stars, last pushed 8d ago), licensed Apache-2.0. It adds 44 tokens to every session and 324 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 skills, from other repositories
new-plugin
Factory line for adding a new HAR verification plugin (like playwright or rocketsim) for any framework — research the framework docs, build the template under src/templates/plugins/, register it everywhere, validate on a real repository, and open a PR. Use when asked to add/create a plugin, plugin template, or…
factory-line
Factory line for executing one station of a declared multi-station program — read the installed line bundle (har line status), plan parallel work into isolated HAR slots, run the cumulative gate with har line gate, and hand off for human review. Use when asked to "run a factory line", "run the next station", "execute…
v1-milestone
Factory line for executing one milestone of the HAR v1.0.0 refactor (epic os-factory/har#225) — plan the wave of parallel subagents, implement each issue in its own HAR slot, ship stacked PRs, run the fixture-e2e milestone gate, and hand off for review. Use when asked to "run the next v1 milestone", "work on v1.0.0"…
lemma-user
Operate an existing Lemma pod from the CLI as a human or agent: inspect resources, query tables and records under RLS, search and read pod files (converted markdown, page images), run functions and workflows, submit waiting workflow forms, chat with pod agents, run first-party tools, and execute third-party connector…
lemma-builder
Design and build complete Lemma pods: model tables/files/functions/agents/workflows/schedules/connectors/surfaces/apps from a problem statement, author a local pod bundle, import progressively with the Lemma CLI, and verify every layer. Use for pod design, creation, restructuring, import/export, and app development.…
lemma-evals
Design, run, and review repeatable evaluations for Lemma agents, functions, and workflows. Use when defining evaluation contracts and case datasets, comparing a baseline with a candidate revision or runtime, checking deterministic correctness or rubric-scored judgment, measuring repeated-run variance, testing…