Borrowing it
Nothing to install: this file belongs to phuoctrung-ppt/ai-sdlc-workflow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/phuoctrung-ppt/ai-sdlc-workflow/master/.cursor/commands/fix.mdgit clone --depth 1 https://github.com/phuoctrung-ppt/ai-sdlc-workflowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/phuoctrung-ppt/ai-sdlc-workflow/fix)<a href="https://agentmods.dev/commands/phuoctrung-ppt/ai-sdlc-workflow/fix"><img src="https://agentmods.dev/badge/commands/phuoctrung-ppt/ai-sdlc-workflow/fix/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/phuoctrung-ppt/ai-sdlc-workflow/fix"><img src="https://agentmods.dev/badge/commands/phuoctrung-ppt/ai-sdlc-workflow/fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00039 | $0.00999 |
| Opus 5.5 | $0.00016 | $0.00400 |
| Sonnet 5.5 | $0.00008 | $0.00200 |
| Haiku 4.5 | $0.00004 | $0.00100 |
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 1mo 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code / Fix Loop (lightweight)
When to use: bug, type error, failing test, small implement, rename, style, patch, regression — anything that does not need a new feature plan or Design Contract.
When NOT to use: new module, new UI surface without existing Design Contract, protected-path architecture change, multi-module feature → use /plan-feature or /dev-module instead.
Act as Orchestrator for a code-loop only.
Hard constraints
- No full plan rewrite. Do not open or recreate
docs/plans/*unless the user explicitly asks to escalate. - No DESIGN-GATE re-run. If the change is pure code/fix on existing UI that already has a Design Contract, implement against that contract. If there is no contract and the change is visual + non-trivial, stop and recommend
/shape-liteor design-spec — do not invent a full marketing redesign. - Context Packet first. Always run context-builder before editing.
- Prefer these skills (already high-signal in manifest):
error-recovery— root-cause fix, never maskagentic-workflow— handoff + scope disciplinesaas-product-ui— only if in-app product UI is touchedfrontend-skills/ domain stack skills — only if paths match
- Scope: stay inside
worker-scopes.json. Escalate if protected paths need change.
Context hygiene
Do not load into context:
.cursor/state/workflow-state.json(use learning-counter CLI if needed).aisdlc/*- full
docs/plans/tree (read only the active plan path if relevant)
Steps
0 — Office + classify
python3 .cursor/scripts/office-event.py --agent architect-planner --status working --task "Code-loop: {issue}" --phase fix --workflow code-loop
Detect intent (expect phase fix, complexity often low):
python3 .cursor/context/intent-detector.py --task "{issue}" --phase fix --paths "{touched_paths}"
1 — Context Packet
python3 .cursor/context/context-builder.py \
--phase fix \
--task "{issue}" \
--agent <narrowest-worker> \
--paths "{touched_paths}" \
--keywords "fix,bug,error,patch" \
--budget 5000
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.
- 1mo ago First seen · 109 lines · 39 tokens per session scan A eed4c56e1360
fix is a command published in the GitHub repository phuoctrung-ppt/ai-sdlc-workflow (2 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 999 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-08.
Other commands, from other repositories
playwright-test-heal
Run all my tests and fix the failing ones.
verify-bug
Post-merge UAT verification workflow. Walks JIRA reproduce steps, performs comparative audits (Before/After), attaches evidence to JIRA, and transitions status on PASS.
bugfix
Bug fix workflow: root cause analysis → user review → regression test + fix via TDD.
api-aqa-flow-execution-and-report-analysis
Phase 6 Execution & Report Analysis of api-aqa-flow (USER INTERACTION REQUIRED).
timeout-fix
A procedure for diagnosing and fixing tests that exceed their time limit by finding causes such as slow processing, hanging network calls, deadlocks, heavy setup, or leaked resources.
AGENTS
Run the current binary in a temporary test repository with a real PTY. Use tmux-cli when available, capture terminal output, and inspect -vv logs when behavior depends on timing or shell state. Avoid treating a piped command as proof of interactive behavior.