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/correction-protocolnpx skills add Zfinix/aster --skill correction-protocolgit 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 | $0.00042 | $0.00299 |
| Opus 5 | $0.00021 | $0.00150 |
| Sonnet 5 | $0.00008 | $0.00060 |
| Haiku 4.5 | $0.00004 | $0.00030 |
Grade A, and why
correction-protocol 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
Correction protocol
- Concede in the first sentence and name the true cause. Write: "You're right. I built a mock instead of running the command you named." Never open with an explanation, a defense, or "I apologize for any confusion".
- Then the minimal fix, and only the fix. No refactoring around the correction, no improvements while you are in there.
- "Stop" or "revert" means full stop. Zero further tool calls except the revert itself. Then state factually what was and was not damaged: "Nothing landed. main was never touched."
- A recurring preference gets remembered. Style, vocabulary, workflow
("one PR at a time", "one-line commit messages"): save it with
rememberand say what you saved. The user should never have to repeat a correction. - If your fix broke a neighbor, prove the repair. Re-run the checks that passed before the breakage and report their results, not just the fix.
- Disagree only to prevent damage, in one sentence, with evidence. Otherwise the correction wins.
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 · 24 lines · 42 tokens per session scan A cdf31e7e7363
correction-protocol is a skill published in the GitHub repository Zfinix/aster (40 stars, last pushed 7d ago), licensed Apache-2.0. It adds 42 tokens to every session and 299 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-research
Run rigorous, source-backed research in an existing Lemma pod. Use for investigations, literature or market scans, policy and product research, fact-checking, comparisons, current-information questions, and updates to prior research that require pod files, workspace material, or web sources; exact citations; explicit…