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/caspian-sun/claude-code-workflow/fixgit clone --depth 1 https://github.com/Caspian-Sun/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 | $0.00000 | $0.04980 |
| Opus 5 | $0.00000 | $0.02490 |
| Sonnet 5 | $0.00000 | $0.00996 |
| Haiku 4.5 | $0.00000 | $0.00498 |
Grade A, and why
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 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 — 431 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are now acting as a Frontend Debugging Engineer. Based on the bug description I provide, locate and fix the issue with minimal impact, verify the fix, and produce a submittable branch/PR.
Input Contract (Important)
The downstream input for this command is always a normalized report conforming to docs/bug-reports/_template.md. Regardless of what the user passes in — free text (one-liner / error stack / repro description) or an existing batch report file (@docs/bug-reports/xxx.md) — Step 0 will first invoke /bug-check to triage and normalize, converting input into a report file before processing. This ensures:
- Triage is complete (only real bugs enter the fix phase)
- All required fields are present (repro / expected / related PRD)
- All bugs have an on-disk report for traceability
Applicable Scenarios
- User verbally reports a bug (with error stack / repro steps) —
/bug-checksolidifies it to a report, then continue - Problem list from
/review→ batch fix /testdiscovers source code violating a business rule → fix source per the rule- Testing AI bug report (
docs/bug-reports/<date>-<module>.md) → batch fix (see "Batch Bug Report Mode" below) - Production logs / Sentry errors (future webhook integration reuses the same flow)
Batch Bug Report Mode (input is @docs/bug-reports/xxx.md)
Trigger Condition
Input starts with @docs/bug-reports/ → automatically enter batch mode.
Report Format Requirements
Report structure follows docs/bug-reports/_template.md and must contain:
- Top-level "Summary" table (Bug ID / priority / module / one-line symptom)
- Each
## Bug B00Xsection with fields: priority / module / related PRD / symptom / repro / expected vs. actual / console errors / network requests / screenshots / root cause hypothesis (optional)
On missing fields:
- Summary table missing →
[BLOCKED]stop, require fill-in before rerunning (cannot group) - Repro steps or expected/actual missing for a single bug → skip that bug and continue; list "skipped bugs" in final report
- Console/network/screenshots missing → allowed; only reduces diagnostic efficiency, does not block
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 · 431 lines · 0 tokens per session scan A 64e8e1b70a2e
fix is a command published in the GitHub repository Caspian-Sun/claude-code-workflow (10 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,980 tokens. 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 commands, from other repositories
concentrate-forces
用集中兵力方法在多个任务中锁定主攻目标。.
spark-prairie-fire
用星火燎原方法为从零起步的任务选择根据地和最小切入口。.
publish-skill
Sync a marketplace skill to the documentation site. Creates skill detail pages (EN/ZH), updates the marketplace index, and updates docs.json navigation.
quick-fix
Fast-track workflow for small bug fixes.
sync-linear
Sync current work with Linear ticket status.
receipts
Find the receipt. A dated line, or it did not happen.