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/robofinsystems/robosystems/hotfixgit clone --depth 1 https://github.com/RoboFinSystems/robosystemsWhat 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 | $0.00033 | $0.01377 |
| Opus 5 | $0.00016 | $0.00688 |
| Sonnet 5 | $0.00007 | $0.00275 |
| Haiku 4.5 | $0.00003 | $0.00138 |
Grade A, and why
hotfix 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship a fix to production ahead of the next release using the two-PR pattern: one PR to main (reviewed; makes the fix permanent) and one PR carrying the same commits to the current release/<x.y.z> branch (CI on the exact ref that will be deployed).
This command is the trigger — never infer a hotfix
A hotfix is a deploy-timing decision with real cost: a second PR, a cherry-pick, and a full production deploy from the release branch. It is chosen by the user, and this command is how they choose it. Do not start this flow from anything else:
- Not from urgency words in a reply — "now", "urgent", "asap", "yes let's do it" after a recommendation to ride the next release.
- Not from the fix touching deployed behavior, a customer-facing surface, or production evidence.
- Not from a memory file, a CLAUDE.md section, or a runbook that describes the pattern.
If a hotfix might be warranted, say so in one line ("this could ship ahead of the release via /hotfix if you want it in prod before then") and stop. Absent /hotfix, a fix goes to main and rides the next release.
How releases work here
create-release.yml cuts a release/<x.y.z> branch, and production deploys from that branch while main keeps moving. So a fix merged only to main waits for the next release, and a fix merged only to the release branch is lost at the next cut. Two PRs, same commits. Committing straight onto the release branch is retired practice: the PR into it is what gets CI run on the ref the deploy will use.
Instructions
1. Preflight
RELEASE=${2:-$(git branch -r | grep 'origin/release/' | sort -V | tail -1 | sed 's#.*origin/##')}
VERSION=${RELEASE#release/} # x.y.z
SUFFIX=$(echo "$VERSION" | tr . -) # x-y-z, for the branch name
git fetch -q origin
- Confirm the bug exists on the release branch. For a regression,
git merge-base --is-ancestor <regressing-merge-sha> origin/$RELEASE; for a long-standing defect,git diff origin/main origin/$RELEASE -- <files>(empty means the same code). If the release branch does not carry the defect, stop — there is nothing to hotfix; say so. - Working tree clean, not on
main. Branch creation goes throughjust create-featureonly. - Security fixes. The twin's diff and body are public the moment they are pushed, often before the deploy lands. Keep both PR bodies terse and non-actionable (the disclosure rules in
/create-prapply to both), and sequence the deploy with — or ahead of — the public push.
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 · 84 lines · 33 tokens per session scan A 2b8610f84468
hotfix is a command published in the GitHub repository RoboFinSystems/robosystems (24 stars, last pushed 3d ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,377 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
fill-event-triage
체결(fill) 이벤트, 특히 매도 체결 후 현금 재배치 판단을 read-only 트리아지로 자동 기동해 dry-run 제안을 남긴다. ROB-755.
crypto-alert-triage
Command "crypto-alert-triage" from mgh3326/auto_trader, covering crypto-alert-triage, 입력, 1. 맥락 복원 (반드시 이 순서), 2. 분석 and 3. dryrun 미리보기 (read-only).
akb-production-review
Review AKB production-governance docs and hooks.
os-meeting
快速创建和管理AI团队会议.
csm-workledger
Show the surviving work-ledger entries across sessions.
scan
Scan AWS account for cost optimization.