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/rbah31/claude-code-workflow/remote-fixnpx skills add rbah31/claude-code-workflow --skill remote-fixgit clone --depth 1 https://github.com/rbah31/claude-code-workflowWhat 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 | $0.00080 | $0.00588 |
| Opus 5 | $0.00040 | $0.00294 |
| Sonnet 5 | $0.00016 | $0.00118 |
| Haiku 4.5 | $0.00008 | $0.00059 |
Grade A, and why
remote-fix 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 3d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remote Fix
You are running a remote fix triggered from outside the terminal (Channels, Dispatch, or manual). The human may have limited context (on phone, at work). Be autonomous but conservative.
Step 1 — Understand the diagnostic
Read the message. Identify:
- What's broken (error, metric, behavior)
- Where (which service, file, endpoint)
- Severity (blocking vs degraded vs cosmetic)
If a Cowork diagnostic file exists in monitoring/, read it. Read tasks/lessons.md for related past issues.
Step 2 — Investigate
Find the root cause. Read logs, grep errors, check recent commits. If the issue is unclear after 5 minutes of investigation, STOP and report what you found — don't guess-fix.
Step 3 — Fix
If the fix is clear and touches ≤ 3 files:
- Create a branch: fix/[description]
- Implement the minimal fix
- Run tests
- Commit with conventional commit message
If the fix is complex (> 3 files, architectural):
- STOP. Report the diagnosis and recommended approach.
- The human decides: fix now or defer to a proper sprint.
Step 4 — PR and report
- Push the branch, create a PR with description
- Report back via Channel: "PR #XX ready — [1-line summary]"
- Wait for human to merge
Step 5 — Verify (after merge)
If the human says "merged" or "verify":
- Check deploy status
- Verify the metric/error is resolved
- Update tasks/lessons.md if this is a new pattern
- Report: "Deploy OK, issue resolved"
STOP. Do not continue to other phases. Do not start a sprint. This is a surgical fix, not a sprint cycle.
Gotchas
- You're being commanded from a phone. Keep responses SHORT. No walls of text. Summary + PR link + status.
- Don't start a full sprint cycle. This is a surgical fix.
- If you're not sure, SAY SO. Better to wait than ship a bad fix.
- Never force-push to main. Always PR, always wait for merge.
- The human may take hours to respond (they're at work). That's normal. Don't spam updates.
- If the diagnostic mentions multiple issues, fix only the most critical one. Add the rest to tasks/backlog.md.
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.
- 3d ago First seen · 74 lines · 80 tokens per session scan A 233e5a83ac1a
remote-fix is a skill published in the GitHub repository rbah31/claude-code-workflow (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 80 tokens to every session and 588 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
moai-ref-git-workflow
Git workflow patterns, branch strategies, conventional commits, and PR templates reference for git operations. Agent-extending skill that amplifies manager-git expertise with production-grade git workflow patterns. NOT for: code implementation, testing, architecture design, documentation content.
flow-next-work
Execute a flow-next spec or task end-to-end with worker subagents, gates, and commits. Use when asked to work on, implement, or execute fn-N.
document
Run /document pr | changelog | release-note | postmortem (or let it ask) to write the human facing prose about a change. Drafts from the real commits and diff, writing to the right place. Does not write code, tests, or specs.
git-commit-helper
Generate conventional commit messages automatically. Use when user runs git commit, stages changes, or asks for commit message help. Analyzes git diff to create clear, descriptive conventional commit messages. Triggers on git commit, staged changes, commit message requests.
commit
Atomic git commit with conventional message. Use when the user says "commit", "save my changes", "commit this", or wants to create a git commit. Stages specific files, writes a conventional commit message with body explaining non-obvious decisions. Never uses git add -A.
commit
Use when 使用者要求把工作區的變更寫進版本歷史，不論用詞是 commit、提交、送進 git 還是「整理一下」；需要拆成多筆時同樣適用。NOT for 把 clade 改動散播到 consumer（走 /clade-publish），NOT for 建 / 合併 worktree（走 /wt）。.